@@ -1980,6 +1980,101 @@ return the hash table order in the parameter. (If the guest is using
the virtualized real-mode area (VRMA) facility, the kernel will
re-create the VMRA HPTEs on the next KVM_RUN of any vcpu.)
+4.77 KVM_S390_CSS_NOTIFY
+
+Capability: KVM_CAP_S390_CSS_SUPPORT
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_css_notify (in)
+Returns: 0 on success, negative value on failure
+
+This ioctl may be used by userspace to notify the kernel that the control
+blocks for a virtual subchannel should be updated and an I/O interrupt
+injected.
+
+It uses the following parameter block:
+
+/* for KVM_S390_CSS_NOTIFY */
+struct kvm_css_notify {
+ __u8 cssid;
+ __u8 ssid;
+ __u16 schid;
+ __u32 scsw[3];
+ __u32 pmcw[7];
+ __u8 sense_data[32];
+ __u8 unsolicited;
+ __u8 func;
+};
+
+cssid, ssid and schid specify the subchannel; scsw, pmcw and sense_data
+are the control blocks to be updated. If the notification is specified
+to be unsolicited, no new interrupt is generated if an interrupt is already
+pending for the subchannel; else an unsolicited interrupt is generated.
+
+The func parameter specifies the asynchronous function that is notified
+for (solicited interrupts only).
+
+This ioctl (like the other interrupt injection ioctls) is executed
+asynchronously to normal vcpu execution.
+
+4.78 KVM_S390_CCW_HOTPLUG
+
+Capability: KVM_CAP_S390_CSS_SUPPORT
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_sch_info (in)
+Returns: 0 on success, negative value on failure
+
+This ioctl allows userspace to notify the kernel about addition or removal
+of subchannels.
+
+It uses the following data structure:
+
+/* for KVM_S390_CCW_HOTPLUG */
+struct kvm_s390_sch_info {
+ __u8 cssid;
+ __u8 ssid;
+ __u16 schid;
+ __u16 devno;
+ __u32 schib[12];
+ int hotplugged;
+ int add;
+ int virtual;
+};
+
+cssid, ssid, schid and devno describe the subchannel. If the subchannel is
+being added, schib contains the initial subchannel information block for it.
+hotplugged (can only be 0 if add is !0) specifies whether the subchannel has
+been dynamically added or removed (as opposed to the initial machine setup,
+when no channel report words will be created). add specifies whether the
+subchannel is coming or going. virtual signifies whether this is a real or
+a purely virtual subchannel.
+
+4.79 KVM_S390_CHP_HOTPLUG
+
+Capability: KVM_CAP_S390_CSS_SUPPORT
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_chp_info (in)
+Returns: 0 on success, negative value on failure
+
+This ioctl allows userspace to notify the kernel about addition or removal
+of a channel path.
+
+It uses the following structure:
+
+/* for KVM_S390_CHP_HOTPLUG */
+struct kvm_s390_chp_info {
+ __u8 cssid;
+ __u8 chpid;
+ __u8 type;
+ int add;
+ int virtual;
+};
+
+cssid and chpid specify the channel path, type the channel path type. add
+determines whether the path is coming or going, and virtual signifies
+whether this is a purely virtual or a real channel path.
5. The kvm_run structure
------------------------
@@ -2195,6 +2290,24 @@ The possible hypercalls are defined in the Power Architecture Platform
Requirements (PAPR) document available from www.power.org (free
developer registration required to access it).
+ /* KVM_EXIT_S390_SCH_IO */
+ struct {
+ __u32 sch_id;
+#define SCH_DO_CSCH 0
+#define SCH_DO_HSCH 1
+#define SCH_DO_SSCH 2
+#define SCH_DO_RSCH 3
+#define SCH_DO_XSCH 4
+ __u8 func;
+ __u8 pad;
+ __u64 orb;
+ __u32 scsw[3];
+ __u32 pmcw[7];
+ } s390_sch_io;
+
+s390 specific. Used for userspace processing of asynchronous subchannel
+functions.
+
/* Fix the size of the union. */
char padding[256];
};
@@ -2316,3 +2429,17 @@ For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
- The tsize field of mas1 shall be set to 4K on TLB0, even though the
hardware ignores this value for TLB0.
+
+6.4 KVM_CAP_S390_CSS_SUPPORT
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables in-kernel support for handling of channel I/O
+instructions like STORE SUBCHANNEL or CHANNEL SUBSYSTEM CALL.
+
+When this capability is enabled, KVM_EXIT_S390_SCH_IO can occur.
+
+When this capability is provided, the KVM_S390_CCW_HOTPLUG,
+KVM_S390_CHP_HOTPLUG and KVM_S390_CSS_NOTIFY ioctls are provided.
@@ -17,13 +17,18 @@
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
#include <asm/debug.h>
+#include <asm/cio.h>
#include <asm/cpu.h>
+#include <asm/crw.h>
#define KVM_MAX_VCPUS 64
#define KVM_MEMORY_SLOTS 32
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 4
+#define VIRTUAL_CSSID 0xfe
+#define KVM_MAX_CSSID 0xfe /* 0xff is reserved */
+
struct sca_entry {
atomic_t scn;
__u32 reserved;
@@ -174,6 +179,7 @@ struct kvm_s390_ext_info {
#define PGM_ADDRESSING 0x05
#define PGM_SPECIFICATION 0x06
#define PGM_DATA 0x07
+#define PGM_OPERAND 0x15
struct kvm_s390_pgm_info {
__u16 code;
@@ -208,6 +214,7 @@ struct kvm_s390_interrupt_info {
struct kvm_s390_prefix_info prefix;
struct kvm_s390_mchk_info mchk;
};
+ int nondyn;
};
/* for local_interrupt.action_flags */
@@ -259,11 +266,52 @@ struct kvm_vm_stat {
struct kvm_arch_memory_slot {
};
+struct crw_container {
+ struct crw crw;
+ struct list_head sibling;
+};
+
+struct chp_info {
+ u8 in_use;
+ u8 type;
+};
+
+struct kvm_subch {
+ struct mutex lock;
+ u8 cssid;
+ u8 ssid;
+ u16 schid;
+ u16 devno;
+ u8 sense_data[32];
+ struct schib *curr_status;
+ struct kvm_s390_interrupt_info inti;
+};
+
+struct schid_info {
+ struct kvm_subch *schs[__MAX_SUBCHANNEL + 1];
+ unsigned long bm[0];
+};
+
+struct kvm_s390_css_data {
+ int max_cssid;
+ int max_ssid;
+ struct list_head pending_crws;
+ struct kvm_s390_interrupt_info crw_inti;
+ int do_crw_mchk;
+ int crws_lost;
+ struct schid_info *schids[KVM_MAX_CSSID + 1][__MAX_SSID + 1];
+ struct chp_info chpids[KVM_MAX_CSSID + 1][__MAX_CHPID + 1];
+ atomic_t chnmon_active;
+ u64 chnmon_area;
+};
+
struct kvm_arch{
struct sca_block *sca;
debug_info_t *dbf;
struct kvm_s390_float_interrupt float_int;
struct gmap *gmap;
+ int css_support;
+ struct kvm_s390_css_data *css;
};
extern int sie64a(struct kvm_s390_sie_block *, u64 *);
@@ -10,5 +10,5 @@ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
-kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o
+kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o ioinst.o css.o
obj-$(CONFIG_KVM) += kvm.o
new file mode 100644
@@ -0,0 +1,945 @@
+/*
+ * Virtual channel subsystem support for kvm
+ *
+ * Copyright IBM Corp. 2012
+ *
+ * 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.
+ *
+ * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <asm/cio.h>
+#include <asm/crw.h>
+#include <asm/schib.h>
+#include <asm/schid.h>
+#include <asm/scsw.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+#include "trace-s390.h"
+
+static void css_update_chnmon(struct kvm_vcpu *vcpu, struct kvm_subch *sch)
+{
+ if (!sch->curr_status->pmcw.mme)
+ /* Not active. */
+ return;
+
+ /*
+ * The only field we want to update (ssch_rsch_count) is conveniently
+ * located at the beginning of the measurement block.
+ * For format 0, it is a 16 bit value; for format 1, a 32 bit value.
+ */
+ if (sch->curr_status->pmcw.mbfc) {
+ /* Format 1, per-subchannel area. */
+ u32 uninitialized_var(count);
+
+ if (get_guest_u32(vcpu, sch->curr_status->mba, &count))
+ return;
+ count++;
+ put_guest_u32(vcpu, sch->curr_status->mba, count);
+ } else {
+ /* Format 0, global area. */
+ u64 target;
+ u16 uninitialized_var(count);
+
+ target = vcpu->kvm->arch.css->chnmon_area +
+ (sch->curr_status->pmcw.mbi << 5);
+ if (get_guest_u16(vcpu, target, &count))
+ return;
+ count++;
+ put_guest_u16(vcpu, target, count);
+ }
+}
+
+static int highest_schid(struct kvm *kvm, u8 cssid, u8 ssid)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+
+ if (!css->schids[cssid][ssid])
+ return 0;
+ return find_last_bit(css->schids[cssid][ssid]->bm,
+ (__MAX_SUBCHANNEL + 1) / sizeof(unsigned long));
+}
+
+int css_schid_final(struct kvm *kvm, u8 cssid, u8 ssid, u16 schid)
+{
+ return (cssid > KVM_MAX_CSSID ||
+ ssid > __MAX_SSID ||
+ schid > highest_schid(kvm, cssid, ssid)) ? 1 : 0;
+}
+
+static int css_add_virtual_chpid(struct kvm *kvm, u8 cssid, u8 chpid, u8 type)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+
+ if (cssid > KVM_MAX_CSSID)
+ return -EINVAL;
+
+ if (css->chpids[cssid][chpid].in_use)
+ return -EEXIST;
+
+ css->chpids[cssid][chpid].in_use = 1;
+ css->chpids[cssid][chpid].type = type;
+ return 0;
+}
+
+static int css_remove_virtual_chpid(struct kvm *kvm, u8 cssid, u8 chpid)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+
+ if (cssid > KVM_MAX_CSSID)
+ return -EINVAL;
+
+ if (!css->chpids[cssid][chpid].in_use)
+ return -EINVAL;
+
+ css->chpids[cssid][chpid].in_use = 0;
+ return 0;
+}
+
+int css_chpid_in_use(struct kvm *kvm, u8 cssid, u8 chpid)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+
+ if ((cssid > KVM_MAX_CSSID) || (chpid > __MAX_CHPID))
+ return 0;
+ return css->chpids[cssid][chpid].in_use;
+}
+
+static int css_chpid_type(struct kvm *kvm, u8 cssid, u8 chpid)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+
+ if ((cssid > KVM_MAX_CSSID) || (chpid > __MAX_CHPID))
+ return 0;
+ return css->chpids[cssid][chpid].type;
+}
+
+int css_collect_chp_desc(struct kvm *kvm, u8 cssid, u8 f_chpid, u8 l_chpid,
+ int rfmt, void *buf)
+{
+ int i, desc_size;
+ u32 words[8];
+
+ desc_size = 0;
+ for (i = f_chpid; i <= l_chpid; i++) {
+ if (!css_chpid_in_use(kvm, cssid, i))
+ continue;
+ if (rfmt == 0) {
+ words[0] = 0x80000000 |
+ (css_chpid_type(kvm, cssid, i) << 8) | i;
+ words[1] = 0;
+ memcpy(buf + desc_size, words, 8);
+ desc_size += 8;
+ } else if (rfmt == 1) {
+ words[0] = 0x80000000 |
+ (css_chpid_type(kvm, cssid, i) << 8) | i;
+ words[1] = 0;
+ words[2] = 0;
+ words[3] = 0;
+ words[4] = 0;
+ words[5] = 0;
+ words[6] = 0;
+ words[7] = 0;
+ memcpy(buf + desc_size, words, 32);
+ desc_size += 32;
+ }
+ }
+ return desc_size;
+}
+
+struct kvm_subch *css_find_subch(struct kvm *kvm, u8 m, u8 cssid, u8 ssid,
+ u16 schid)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+ u8 real_cssid;
+
+ if (!m) {
+ if (cssid)
+ return NULL;
+ real_cssid = VIRTUAL_CSSID;
+ } else
+ real_cssid = cssid;
+ /* Don't bother for out of range values. */
+ if (css_schid_final(kvm, real_cssid, ssid, schid))
+ return NULL;
+ if (!css->schids[real_cssid][ssid])
+ return NULL;
+ if (!test_bit(schid, css->schids[real_cssid][ssid]->bm))
+ return NULL;
+ return css->schids[real_cssid][ssid]->schs[schid];
+}
+
+void css_queue_crw(struct kvm *kvm, u8 rsc, u8 erc, int chain, u16 rsid)
+{
+ struct crw_container *crw_cont;
+ struct kvm_s390_css_data *css = kvm->arch.css;
+ int ret;
+
+ /* TODO: Maybe use a static crw pool? */
+ crw_cont = kzalloc(sizeof(struct crw_container), GFP_KERNEL);
+
+ mutex_lock(&kvm->lock);
+
+ if (!crw_cont) {
+ css->crws_lost = 1;
+ goto out;
+ }
+ crw_cont->crw.rsc = rsc;
+ crw_cont->crw.erc = erc;
+ crw_cont->crw.chn = chain;
+ crw_cont->crw.rsid = rsid;
+ crw_cont->crw.oflw = css->crws_lost;
+ css->crws_lost = 0;
+
+ list_add_tail(&crw_cont->sibling, &css->pending_crws);
+
+ if (css->do_crw_mchk) {
+ css->do_crw_mchk = 0;
+ ret = kvm_s390_inject_internal(kvm, &css->crw_inti);
+ if (ret)
+ css->do_crw_mchk = 1;
+ }
+out:
+ mutex_unlock(&kvm->lock);
+}
+
+int css_do_stcrw(struct kvm_vcpu *vcpu, u32 cda)
+{
+ struct crw_container *crw_cont;
+ struct kvm_s390_css_data *css = vcpu->kvm->arch.css;
+ int ret;
+
+ mutex_lock(&vcpu->kvm->lock);
+ if (list_empty(&css->pending_crws)) {
+ u32 zeroes = 0;
+ /* List was empty, turn crw machine checks on again. */
+ if (copy_to_guest(vcpu, cda, &zeroes, sizeof(struct crw))) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ ret = -EIO;
+ goto out;
+ }
+ css->do_crw_mchk = 1;
+ ret = 1;
+ goto out;
+ }
+
+ crw_cont = container_of(css->pending_crws.next, struct crw_container,
+ sibling);
+ if (copy_to_guest(vcpu, cda, &crw_cont->crw, sizeof(struct crw))) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ ret = -EIO;
+ goto out;
+ }
+ list_del(&crw_cont->sibling);
+ kfree(crw_cont);
+ ret = 0;
+out:
+ mutex_unlock(&vcpu->kvm->lock);
+ return ret;
+}
+
+void css_do_schm(struct kvm_vcpu *vcpu, u8 mbk, int update, int dct, u64 mbo)
+{
+ struct kvm_s390_css_data *css = vcpu->kvm->arch.css;
+
+ /* dct is currently ignored (not really meaningful for our devices) */
+ /* TODO: Don't ignore mbk. */
+ if (update && !atomic_cmpxchg(&css->chnmon_active, 0, 1))
+ /* Enable measuring. */
+ css->chnmon_area = mbo;
+
+ if (!update && !atomic_cmpxchg(&css->chnmon_active, 1, 0))
+ /* Disable measuring. */
+ css->chnmon_area = 0;
+}
+
+int css_enable_mcsse(struct kvm *kvm)
+{
+ kvm->arch.css->max_cssid = KVM_MAX_CSSID;
+ return 0;
+}
+
+int css_enable_mss(struct kvm *kvm)
+{
+ kvm->arch.css->max_ssid = __MAX_SSID;
+ return 0;
+}
+
+int css_do_tpi(struct kvm_vcpu *vcpu, u32 addr, int lowcore)
+{
+ struct kvm_s390_interrupt_info *inti;
+
+ inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->run->s.regs.crs[6]);
+ if (inti) {
+ if (!lowcore) {
+ put_guest_u16(vcpu, addr, inti->io.subchannel_id);
+ put_guest_u16(vcpu, addr + 2, inti->io.subchannel_nr);
+ put_guest_u32(vcpu, addr + 4, inti->io.io_int_parm);
+ } else {
+ put_guest_u16(vcpu, addr + 184, inti->io.subchannel_id);
+ put_guest_u16(vcpu, addr + 186, inti->io.subchannel_nr);
+ put_guest_u32(vcpu, addr + 188, inti->io.io_int_parm);
+ put_guest_u32(vcpu, addr + 192, inti->io.io_int_word);
+ }
+ return 1;
+ }
+ return 0;
+}
+
+int css_do_msch(struct kvm_vcpu *vcpu, struct kvm_subch *sch,
+ struct schib *schib)
+{
+ union scsw *s = &sch->curr_status->scsw;
+ struct pmcw *p = &sch->curr_status->pmcw;
+ int ret;
+
+ mutex_lock(&sch->lock);
+
+ if (!sch->curr_status->pmcw.dnv) {
+ ret = 0;
+ goto out;
+ }
+
+ if (scsw_stctl(s) & SCSW_STCTL_STATUS_PEND) {
+ ret = -EINPROGRESS;
+ goto out;
+ }
+
+ if (scsw_fctl(s) & (SCSW_FCTL_START_FUNC | SCSW_FCTL_HALT_FUNC |
+ SCSW_FCTL_CLEAR_FUNC)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Only update the program-modifiable fields. */
+ p->ena = schib->pmcw.ena;
+ p->intparm = schib->pmcw.intparm;
+ p->isc = schib->pmcw.isc;
+ p->mp = schib->pmcw.mp;
+ p->lpm = schib->pmcw.lpm;
+ p->pom = schib->pmcw.pom;
+ p->lm = schib->pmcw.lm;
+ p->csense = schib->pmcw.csense;
+
+ p->mme = schib->pmcw.mme;
+ p->mbi = schib->pmcw.mbi;
+ p->mbfc = schib->pmcw.mbfc;
+ sch->curr_status->mba = schib->mba;
+
+ /*
+ * No need to exit to userspace since it will get the current state
+ * with the next exit.
+ */
+ ret = 0;
+
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+int css_do_xsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch)
+{
+ union scsw *s = &sch->curr_status->scsw;
+ struct pmcw *p = &sch->curr_status->pmcw;
+ int ret;
+
+ mutex_lock(&sch->lock);
+
+ if (!p->dnv || !p->ena) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (!scsw_fctl(s) || (scsw_fctl(s) != SCSW_FCTL_START_FUNC) ||
+ (!(scsw_actl(s) & (SCSW_ACTL_RESUME_PEND | SCSW_ACTL_START_PEND |
+ SCSW_ACTL_SUSPENDED))) ||
+ (scsw_actl(s) & SCSW_ACTL_SCHACT)) {
+ ret = -EINPROGRESS;
+ goto out;
+ }
+
+ if (scsw_stctl(s) != 0) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Cancel the current operation. */
+ s->cmd.fctl &= ~SCSW_FCTL_START_FUNC;
+ s->cmd.actl &= ~(SCSW_ACTL_RESUME_PEND | SCSW_ACTL_START_PEND |
+ SCSW_ACTL_SUSPENDED);
+ s->cmd.dstat = 0;
+ s->cmd.cstat = 0;
+ /*
+ * Let userspace update its state.
+ * No hardware related structures need to be updated, since userspace
+ * will get the current state with the next exit.
+ */
+ vcpu->run->exit_reason = KVM_EXIT_S390_SCH_IO;
+ vcpu->run->s390_sch_io.func = SCH_DO_XSCH;
+ vcpu->run->s390_sch_io.sch_id = (sch->cssid << 24) | (1 << 19) |
+ (sch->ssid << 17) | 1 << 16 | sch->schid;
+ ret = -EREMOTE;
+
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+int css_do_csch(struct kvm_vcpu *vcpu, struct kvm_subch *sch)
+{
+ union scsw *s = &sch->curr_status->scsw;
+ struct pmcw *p = &sch->curr_status->pmcw;
+ int ret;
+
+ mutex_lock(&sch->lock);
+
+ if (!p->dnv || !p->ena) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ /* Trigger the clear function. */
+ s->cmd.fctl = SCSW_FCTL_CLEAR_FUNC;
+ s->cmd.actl = SCSW_ACTL_CLEAR_PEND;
+
+ /* Let userspace handle the clear function. */
+ vcpu->run->exit_reason = KVM_EXIT_S390_SCH_IO;
+ vcpu->run->s390_sch_io.func = SCH_DO_CSCH;
+ vcpu->run->s390_sch_io.sch_id = (sch->cssid << 24) | (1 << 19) |
+ (sch->ssid << 17) | 1 << 16 | sch->schid;
+ memcpy(&vcpu->run->s390_sch_io.scsw, s, sizeof(*s));
+ memcpy(&vcpu->run->s390_sch_io.pmcw, p, sizeof(*p));
+ ret = -EREMOTE;
+
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+int css_do_hsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch)
+{
+ union scsw *s = &sch->curr_status->scsw;
+ struct pmcw *p = &sch->curr_status->pmcw;
+ int ret;
+
+ mutex_lock(&sch->lock);
+
+ if (!p->dnv || !p->ena) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if ((scsw_stctl(s) == SCSW_STCTL_STATUS_PEND) ||
+ (scsw_stctl(s) & (SCSW_STCTL_PRIM_STATUS |
+ SCSW_STCTL_SEC_STATUS |
+ SCSW_STCTL_ALERT_STATUS))) {
+ ret = -EINPROGRESS;
+ goto out;
+ }
+
+ if (scsw_fctl(s) & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Trigger the halt function. */
+ s->cmd.fctl |= SCSW_FCTL_HALT_FUNC;
+ s->cmd.fctl &= ~SCSW_FCTL_START_FUNC;
+ if ((scsw_actl(s) == (SCSW_ACTL_SCHACT | SCSW_ACTL_DEVACT)) &&
+ (scsw_stctl(s) == SCSW_STCTL_INTER_STATUS)) {
+ s->cmd.stctl &= ~SCSW_STCTL_STATUS_PEND;
+ }
+ s->cmd.actl |= SCSW_ACTL_HALT_PEND;
+
+ /* Let userspace handle the halt function. */
+ vcpu->run->exit_reason = KVM_EXIT_S390_SCH_IO;
+ vcpu->run->s390_sch_io.func = SCH_DO_HSCH;
+ vcpu->run->s390_sch_io.sch_id = (sch->cssid << 24) | (1 << 19) |
+ (sch->ssid << 17) | 1 << 16 | sch->schid;
+ memcpy(&vcpu->run->s390_sch_io.scsw, s, sizeof(*s));
+ memcpy(&vcpu->run->s390_sch_io.pmcw, p, sizeof(*p));
+ ret = -EREMOTE;
+
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+int css_do_ssch(struct kvm_vcpu *vcpu, struct kvm_subch *sch, u64 orb)
+{
+ union scsw *s = &sch->curr_status->scsw;
+ struct pmcw *p = &sch->curr_status->pmcw;
+ int ret;
+
+ mutex_lock(&sch->lock);
+
+ if (!p->dnv || !p->ena) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (scsw_stctl(s) & SCSW_STCTL_STATUS_PEND) {
+ ret = -EINPROGRESS;
+ goto out;
+ }
+
+ if (scsw_fctl(s) & (SCSW_FCTL_START_FUNC |
+ SCSW_FCTL_HALT_FUNC |
+ SCSW_FCTL_CLEAR_FUNC)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* If monitoring is active, update counter. */
+ if (atomic_read(&vcpu->kvm->arch.css->chnmon_active))
+ css_update_chnmon(vcpu, sch);
+
+ /* Trigger the start function. */
+ s->cmd.fctl |= SCSW_FCTL_START_FUNC;
+ s->cmd.actl |= SCSW_ACTL_START_PEND;
+ s->cmd.pno = 0;
+
+ /* Let userspace handle the start function. */
+ vcpu->run->exit_reason = KVM_EXIT_S390_SCH_IO;
+ vcpu->run->s390_sch_io.func = SCH_DO_SSCH;
+ vcpu->run->s390_sch_io.sch_id = (sch->cssid << 24) | (1 << 19) |
+ (sch->ssid << 17) | 1 << 16 | sch->schid;
+ memcpy(&vcpu->run->s390_sch_io.scsw, s, sizeof(*s));
+ memcpy(&vcpu->run->s390_sch_io.pmcw, p, sizeof(*p));
+ vcpu->run->s390_sch_io.orb = orb;
+ ret = -EREMOTE;
+
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+int css_do_tsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch, uint32_t addr)
+{
+ union scsw *s = &sch->curr_status->scsw;
+ struct pmcw *p = &sch->curr_status->pmcw;
+ u8 stctl;
+ u8 fctl;
+ u8 actl;
+ struct irb irb;
+ int ret;
+ u32 *esw;
+
+
+ mutex_lock(&sch->lock);
+
+ if (!p->dnv || !p->ena) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ stctl = scsw_stctl(s);
+ fctl = scsw_fctl(s);
+ actl = scsw_actl(s);
+
+ memset(&irb, 0, sizeof(struct irb));
+
+ /* Copy scsw. */
+ memcpy(&irb.scsw, s, sizeof(union scsw));
+ esw = (u32 *)&irb.esw;
+ if (stctl & SCSW_STCTL_STATUS_PEND) {
+ if (scsw_cstat(s) & (SCHN_STAT_CHN_DATA_CHK |
+ SCHN_STAT_CHN_CTRL_CHK |
+ SCHN_STAT_INTF_CTRL_CHK)) {
+ irb.scsw.cmd.eswf = 1;
+ esw[0] = 0x04804000;
+ } else
+ esw[0] = 0x00800000;
+
+ /* If a unit check is pending, copy sense data. */
+ if ((scsw_dstat(s) & DEV_STAT_UNIT_CHECK) && p->csense) {
+ irb.scsw.cmd.eswf = 1;
+ irb.scsw.cmd.ectl = 1;
+ memcpy(irb.ecw, sch->sense_data,
+ sizeof(sch->sense_data));
+ esw[1] = 0x02000000 | (sizeof(sch->sense_data) << 8);
+ }
+ }
+ if (copy_to_guest(vcpu, addr, &irb, sizeof(struct irb))) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ ret = -EIO;
+ goto out;
+ }
+
+ /* Clear conditions on subchannel, if applicable. */
+ if (stctl & SCSW_STCTL_STATUS_PEND) {
+ s->cmd.stctl = 0;
+ if ((stctl != (SCSW_STCTL_INTER_STATUS |
+ SCSW_STCTL_STATUS_PEND)) ||
+ ((fctl & SCSW_FCTL_HALT_FUNC) &&
+ (actl & SCSW_ACTL_SUSPENDED)))
+ s->cmd.fctl = 0;
+
+ if (stctl != (SCSW_STCTL_INTER_STATUS |
+ SCSW_STCTL_STATUS_PEND)) {
+ s->cmd.pno = 0;
+ s->cmd.actl &= ~(SCSW_ACTL_RESUME_PEND |
+ SCSW_ACTL_START_PEND |
+ SCSW_ACTL_HALT_PEND |
+ SCSW_ACTL_CLEAR_PEND |
+ SCSW_ACTL_SUSPENDED);
+ } else {
+ if ((actl & SCSW_ACTL_SUSPENDED) &&
+ (fctl & SCSW_FCTL_START_FUNC)) {
+ s->cmd.pno = 0;
+ if (fctl & SCSW_FCTL_HALT_FUNC)
+ s->cmd.actl &= ~(SCSW_ACTL_RESUME_PEND |
+ SCSW_ACTL_START_PEND |
+ SCSW_ACTL_HALT_PEND |
+ SCSW_ACTL_CLEAR_PEND |
+ SCSW_ACTL_SUSPENDED);
+ else
+ s->cmd.actl &= ~SCSW_ACTL_RESUME_PEND;
+ }
+ /* Clear a possible pending I/O interrupt. */
+ if (!list_empty(&sch->inti.list))
+ kvm_s390_dequeue_internal(vcpu->kvm, &sch->inti);
+ }
+ /* Clear pending sense data. */
+ if (p->csense)
+ memset(sch->sense_data, 0 , sizeof(sch->sense_data));
+ }
+
+ /*
+ * No need to exit to userspace since it will get the current state
+ * with the next exit.
+ */
+ ret = (stctl & SCSW_STCTL_STATUS_PEND) ? -EBUSY : 0;
+
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+int css_do_rsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch)
+{
+ union scsw *s = &sch->curr_status->scsw;
+ struct pmcw *p = &sch->curr_status->pmcw;
+ int ret;
+
+ mutex_lock(&sch->lock);
+
+ if (!p->dnv || !p->ena) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (scsw_stctl(s) & SCSW_STCTL_STATUS_PEND) {
+ ret = -EINPROGRESS;
+ goto out;
+ }
+
+ if ((scsw_fctl(s) != SCSW_FCTL_START_FUNC) ||
+ (scsw_actl(s) & SCSW_ACTL_RESUME_PEND) ||
+ (!(scsw_actl(s) & SCSW_ACTL_SUSPENDED))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* If monitoring is active, update counter. */
+ if (atomic_read(&vcpu->kvm->arch.css->chnmon_active))
+ css_update_chnmon(vcpu, sch);
+
+ s->cmd.actl |= SCSW_ACTL_RESUME_PEND;
+ /* Let userspace handle the start function. */
+ vcpu->run->exit_reason = KVM_EXIT_S390_SCH_IO;
+ vcpu->run->s390_sch_io.func = SCH_DO_RSCH;
+ vcpu->run->s390_sch_io.sch_id = (sch->cssid << 24) | (1 << 19) |
+ (sch->ssid << 17) | 1 << 16 | sch->schid;
+ memcpy(&vcpu->run->s390_sch_io.scsw, s, sizeof(*s));
+ memcpy(&vcpu->run->s390_sch_io.pmcw, p, sizeof(*p));
+ ret = -EREMOTE;
+
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+int kvm_arch_vcpu_ioctl_css_notify(struct kvm_vcpu *vcpu,
+ struct kvm_css_notify *notify)
+{
+ struct kvm_subch *sch;
+ int ret;
+
+ trace_kvm_s390_css_notify(notify->cssid, notify->ssid, notify->schid);
+ /* Userspace always gives us the real cssid. */
+ sch = css_find_subch(vcpu->kvm, 1, notify->cssid, notify->ssid,
+ notify->schid);
+ if (!sch)
+ return -ENODEV;
+ mutex_lock(&sch->lock);
+ if (notify->unsolicited) {
+ /*
+ * Userspace wants us to inject an unsolicited interrupt
+ * iff the subchannel is not status pending.
+ */
+ if (scsw_stctl(&sch->curr_status->scsw) &
+ SCSW_STCTL_STATUS_PEND) {
+ ret = 0;
+ goto out;
+ }
+ sch->curr_status->scsw.cmd.stctl =
+ SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND;
+ } else {
+ /*
+ * First, check whether any I/O instructions have been
+ * issued in the mean time which would preclude normal
+ * signalling as requested by the control block. This
+ * might happen e.g. if the kernel accepted a csch while
+ * the start function was in progress in user space.
+ */
+ if (((notify->func == SCH_DO_SSCH) ||
+ (notify->func == SCH_DO_RSCH)) &&
+ (scsw_fctl(&sch->curr_status->scsw) != SCSW_FCTL_START_FUNC)) {
+ /*
+ * xsch, hsch, or csch happened.
+ * For the xsch case, no interrupt will be generated.
+ * For the hsch/csch case, another notification will
+ * happen.
+ */
+ ret = 0;
+ goto out;
+ }
+ if ((notify->func == SCH_DO_HSCH) &&
+ (scsw_fctl(&sch->curr_status->scsw) & SCSW_FCTL_CLEAR_FUNC)) {
+ /*
+ * csch happened, and another notification will come
+ * in later.
+ */
+ ret = 0;
+ goto out;
+ }
+ /* Update internal status. */
+ memcpy(&sch->curr_status->scsw, ¬ify->scsw,
+ sizeof(notify->scsw));
+ memcpy(&sch->curr_status->pmcw, ¬ify->pmcw,
+ sizeof(notify->pmcw));
+ memcpy(sch->sense_data, notify->sense_data,
+ sizeof(notify->sense_data));
+ }
+
+ /* Inject interrupt. */
+ sch->inti.type = (sch->cssid << 24) | (sch->ssid << 22) |
+ (sch->schid << 16);
+ sch->inti.io.subchannel_id = vcpu->kvm->arch.css->max_cssid > 0 ?
+ (sch->cssid << 8) | (1 << 3) | (sch->ssid << 1) | 1 :
+ (sch->ssid << 1) | 1;
+ sch->inti.io.subchannel_nr = sch->schid;
+ sch->inti.io.io_int_parm = sch->curr_status->pmcw.intparm;
+ sch->inti.io.io_int_word = (0x80 >> sch->curr_status->pmcw.isc) << 24;
+ BUG_ON(!list_empty(&sch->inti.list));
+ mutex_lock(&vcpu->kvm->lock);
+ ret = kvm_s390_inject_internal(vcpu->kvm, &sch->inti);
+ mutex_unlock(&vcpu->kvm->lock);
+out:
+ mutex_unlock(&sch->lock);
+ return ret;
+}
+
+static int css_add_to_store(struct kvm *kvm, struct kvm_subch *sch)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+ struct schid_info *info;
+ size_t schid_size;
+
+ if (!css->schids[sch->cssid][sch->ssid]) {
+ schid_size = sizeof(struct schid_info) +
+ __BITOPS_WORDS(__MAX_SUBCHANNEL + 1) *
+ sizeof(unsigned long);
+ css->schids[sch->cssid][sch->ssid] = vmalloc(schid_size);
+ if (!css->schids[sch->cssid][sch->ssid])
+ return -ENOMEM;
+ memset(css->schids[sch->cssid][sch->ssid], 0, schid_size);
+ }
+ info = css->schids[sch->cssid][sch->ssid];
+ info->schs[sch->schid] = sch;
+ set_bit(sch->schid, info->bm);
+
+ return 0;
+}
+
+static int css_remove_from_store(struct kvm *kvm, struct kvm_subch *sch)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+ struct schid_info *info;
+
+ info = css->schids[sch->cssid][sch->ssid];
+ if (!info)
+ return -EINVAL;
+ info->schs[sch->schid] = NULL;
+ clear_bit(sch->schid, info->bm);
+
+ return 0;
+}
+
+static int css_add_subchannel(struct kvm *kvm,
+ struct kvm_s390_sch_info *sch_info)
+{
+ struct kvm_subch *sch;
+ struct kvm_s390_css_data *css = kvm->arch.css;
+ u8 guest_cssid;
+ bool no_crw;
+
+ /* Generate subchannel structure. */
+ sch = kzalloc(sizeof(*sch), GFP_KERNEL);
+ if (!sch)
+ return -ENOMEM;
+ sch->curr_status = kzalloc(sizeof(*sch->curr_status), GFP_KERNEL);
+ if (!sch->curr_status) {
+ kfree(sch);
+ return -ENOMEM;
+ }
+ mutex_init(&sch->lock);
+ sch->cssid = sch_info->cssid;
+ sch->ssid = sch_info->ssid;
+ sch->schid = sch_info->schid;
+ sch->devno = sch_info->devno;
+ memcpy(sch->curr_status, &sch_info->schib, sizeof(*sch->curr_status));
+ INIT_LIST_HEAD(&sch->inti.list);
+ sch->inti.nondyn = 1;
+ /* Add subchannel to store. */
+ css_add_to_store(kvm, sch);
+ if (!sch_info->hotplugged)
+ goto out;
+ /*
+ * Generate add ccw.
+ *
+ * Only notify for higher subchannel sets/channel subsystems if the
+ * guest has enabled it.
+ */
+ guest_cssid = ((css->max_cssid == 0) && (sch->cssid == VIRTUAL_CSSID)) ?
+ 0 : sch->cssid;
+ no_crw = (sch->ssid > css->max_ssid) ||
+ (guest_cssid > css->max_cssid) ||
+ ((css->max_cssid == 0) && (sch->cssid != VIRTUAL_CSSID));
+ if (!no_crw) {
+ css_queue_crw(kvm, CRW_RSC_SCH, CRW_ERC_IPARM,
+ ((css->max_ssid > 0) || (css->max_cssid > 0)) ?
+ 1 : 0, sch->schid);
+ if ((css->max_ssid > 0) || (css->max_cssid > 0))
+ css_queue_crw(kvm, CRW_RSC_SCH, CRW_ERC_IPARM, 0,
+ (guest_cssid << 8) | (sch->ssid << 4));
+ }
+out:
+ return 0;
+}
+
+static int css_remove_subchannel(struct kvm *kvm, struct kvm_subch *sch)
+{
+ struct kvm_s390_css_data *css = kvm->arch.css;
+ u8 guest_cssid;
+ bool no_crw;
+
+ /* Make subchannel inaccessible. */
+ mutex_lock(&sch->lock);
+ /* Clear a possible pending I/O interrupt. */
+ if (!list_empty(&sch->inti.list))
+ kvm_s390_dequeue_internal(kvm, &sch->inti);
+ css_remove_from_store(kvm, sch);
+ mutex_unlock(&sch->lock);
+ /*
+ * Generate removal ccw.
+ *
+ * Only notify for higher subchannel sets/channel subsystems if the
+ * guest has enabled it.
+ */
+ guest_cssid = ((css->max_cssid == 0) && (sch->cssid == VIRTUAL_CSSID)) ?
+ 0 : sch->cssid;
+ no_crw = (sch->ssid > css->max_ssid) ||
+ (guest_cssid > css->max_cssid) ||
+ ((css->max_cssid == 0) && (sch->cssid != VIRTUAL_CSSID));
+ if (!no_crw) {
+ css_queue_crw(kvm, CRW_RSC_SCH, CRW_ERC_IPARM,
+ ((css->max_ssid > 0) || (css->max_cssid > 0)) ?
+ 1 : 0, sch->schid);
+ if ((css->max_ssid > 0) || (css->max_cssid > 0))
+ css_queue_crw(kvm, CRW_RSC_SCH, CRW_ERC_IPARM, 0,
+ (guest_cssid << 8) | (sch->ssid << 4));
+ }
+ kfree(sch);
+ return 0;
+}
+
+int kvm_s390_process_ccw_hotplug(struct kvm *kvm,
+ struct kvm_s390_sch_info *sch_info)
+{
+ struct kvm_subch *sch;
+
+ trace_kvm_s390_ccw_hotplug(sch_info->cssid, sch_info->ssid,
+ sch_info->schid, sch_info->add);
+ /* We currently support only virtual subchannels. */
+ if (!sch_info->virtual)
+ return -EINVAL;
+
+ /* Virtual subchannels must be in the virtual css. */
+ if (sch_info->virtual && (sch_info->cssid != VIRTUAL_CSSID))
+ return -EINVAL;
+ /* Userspace always notifies with the real cssid. */
+ sch = css_find_subch(kvm, 1, sch_info->cssid, sch_info->ssid,
+ sch_info->schid);
+ if (sch_info->add) {
+ /* New device. */
+ if (sch)
+ return -EINVAL;
+ return css_add_subchannel(kvm, sch_info);
+ } else {
+ /* Device gone. */
+ if (!sch)
+ return -EINVAL;
+ return css_remove_subchannel(kvm, sch);
+ }
+}
+
+int kvm_s390_process_chp_hotplug(struct kvm *kvm,
+ struct kvm_s390_chp_info *chp_info)
+{
+ if (!chp_info->virtual)
+ /* Not supported for now. */
+ return -EINVAL;
+
+ /* Virtual channel paths must be in the virtual css. */
+ if (chp_info->virtual && (chp_info->cssid != VIRTUAL_CSSID))
+ return -EINVAL;
+ if (chp_info->add)
+ return css_add_virtual_chpid(kvm, chp_info->cssid,
+ chp_info->chpid, chp_info->type);
+ else
+ return css_remove_virtual_chpid(kvm, chp_info->cssid,
+ chp_info->chpid);
+}
+
+int kvm_s390_enable_css(struct kvm *kvm)
+{
+ if (kvm->arch.css_support)
+ return 0;
+
+ kvm->arch.css = kzalloc(sizeof(*kvm->arch.css), GFP_KERNEL);
+ if (!kvm->arch.css)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&kvm->arch.css->pending_crws);
+ INIT_LIST_HEAD(&kvm->arch.css->crw_inti.list);
+ kvm->arch.css->crw_inti.type = KVM_S390_MCHK;
+ kvm->arch.css->crw_inti.mchk.mcic = 0x00400f1d40330000;
+ kvm->arch.css->crw_inti.mchk.cr14 = 1 << 28;
+ kvm->arch.css->crw_inti.nondyn = 1;
+ kvm->arch.css->do_crw_mchk = 1;
+ atomic_set(&kvm->arch.css->chnmon_active, 0);
+ kvm->arch.css_support = 1;
+ trace_kvm_s390_enable_kernel_css(kvm);
+ return 0;
+}
@@ -273,6 +273,7 @@ static const intercept_handler_t intercept_funcs[] = {
[0x0C >> 2] = handle_instruction_and_prog,
[0x10 >> 2] = handle_noop,
[0x14 >> 2] = handle_noop,
+ [0x18 >> 2] = handle_noop,
[0x1C >> 2] = kvm_s390_handle_wait,
[0x20 >> 2] = handle_validity,
[0x28 >> 2] = handle_stop,
@@ -370,6 +370,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
__LC_MCK_NEW_PSW, sizeof(psw_t));
+
if (rc == -EFAULT)
exception = 1;
break;
@@ -596,7 +597,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
spin_lock_bh(&li->lock);
list_for_each_entry_safe(inti, n, &li->list, list) {
if (__interrupt_is_deliverable(vcpu, inti)) {
- list_del(&inti->list);
+ list_del_init(&inti->list);
deliver = 1;
break;
}
@@ -607,7 +608,8 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
spin_unlock_bh(&li->lock);
if (deliver) {
__do_deliver_interrupt(vcpu, inti);
- kfree(inti);
+ if (!inti->nondyn)
+ kfree(inti);
}
} while (deliver);
}
@@ -622,7 +624,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
spin_lock(&fi->lock);
list_for_each_entry_safe(inti, n, &fi->list, list) {
if (__interrupt_is_deliverable(vcpu, inti)) {
- list_del(&inti->list);
+ list_del_init(&inti->list);
deliver = 1;
break;
}
@@ -633,7 +635,8 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
spin_unlock(&fi->lock);
if (deliver) {
__do_deliver_interrupt(vcpu, inti);
- kfree(inti);
+ if (!inti->nondyn)
+ kfree(inti);
}
} while (deliver);
}
@@ -654,7 +657,7 @@ void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
list_for_each_entry_safe(inti, n, &li->list, list) {
if ((inti->type == KVM_S390_MCHK) &&
__interrupt_is_deliverable(vcpu, inti)) {
- list_del(&inti->list);
+ list_del_init(&inti->list);
deliver = 1;
break;
}
@@ -665,7 +668,8 @@ void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
spin_unlock_bh(&li->lock);
if (deliver) {
__do_deliver_interrupt(vcpu, inti);
- kfree(inti);
+ if (!inti->nondyn)
+ kfree(inti);
}
} while (deliver);
}
@@ -677,7 +681,7 @@ void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
list_for_each_entry_safe(inti, n, &fi->list, list) {
if ((inti->type == KVM_S390_MCHK) &&
__interrupt_is_deliverable(vcpu, inti)) {
- list_del(&inti->list);
+ list_del_init(&inti->list);
deliver = 1;
break;
}
@@ -688,7 +692,8 @@ void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
spin_unlock(&fi->lock);
if (deliver) {
__do_deliver_interrupt(vcpu, inti);
- kfree(inti);
+ if (!inti->nondyn)
+ kfree(inti);
}
} while (deliver);
}
@@ -716,14 +721,100 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
return 0;
}
-int kvm_s390_inject_vm(struct kvm *kvm,
- struct kvm_s390_interrupt *s390int)
+int kvm_s390_inject_internal(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti)
{
struct kvm_s390_local_interrupt *li;
struct kvm_s390_float_interrupt *fi;
- struct kvm_s390_interrupt_info *inti, *iter;
+ struct kvm_s390_interrupt_info *iter;
int sigcpu;
+ fi = &kvm->arch.float_int;
+ spin_lock(&fi->lock);
+ if (!is_ioint(inti->type))
+ list_add_tail(&inti->list, &fi->list);
+ else {
+ /* Keep I/O interrupts sorted in isc order. */
+ list_for_each_entry(iter, &fi->list, list) {
+ if (!is_ioint(iter->type))
+ continue;
+ if (iter->io.io_int_word <= inti->io.io_int_word)
+ continue;
+ break;
+ }
+ list_add_tail(&inti->list, &iter->list);
+ }
+ atomic_set(&fi->active, 1);
+ sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
+ if (sigcpu == KVM_MAX_VCPUS) {
+ do {
+ sigcpu = fi->next_rr_cpu++;
+ if (sigcpu == KVM_MAX_VCPUS)
+ sigcpu = fi->next_rr_cpu = 0;
+ } while (fi->local_int[sigcpu] == NULL);
+ }
+ li = fi->local_int[sigcpu];
+ spin_lock_bh(&li->lock);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ if (waitqueue_active(&li->wq))
+ wake_up_interruptible(&li->wq);
+ spin_unlock_bh(&li->lock);
+ spin_unlock(&fi->lock);
+ return 0;
+}
+
+int kvm_s390_dequeue_internal(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti)
+{
+ struct kvm_s390_float_interrupt *fi;
+
+ if (!inti)
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+ fi = &kvm->arch.float_int;
+ spin_lock(&fi->lock);
+ list_del_init(&inti->list);
+ if (list_empty(&fi->list))
+ atomic_set(&fi->active, 0);
+ spin_unlock(&fi->lock);
+ mutex_unlock(&kvm->lock);
+ return 0;
+}
+
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, u64 cr6)
+{
+ struct kvm_s390_float_interrupt *fi;
+ struct kvm_s390_interrupt_info *inti, *iter;
+
+ mutex_lock(&kvm->lock);
+ fi = &kvm->arch.float_int;
+ spin_lock(&fi->lock);
+ inti = NULL;
+ list_for_each_entry(iter, &fi->list, list) {
+ if (!is_ioint(iter->type))
+ continue;
+ if ((cr6 & iter->io.io_int_word) == 0)
+ continue;
+ inti = iter;
+ break;
+ }
+ if (inti)
+ list_del_init(&inti->list);
+ if (list_empty(&fi->list))
+ atomic_set(&fi->active, 0);
+ spin_unlock(&fi->lock);
+ mutex_unlock(&kvm->lock);
+ return inti;
+}
+
+
+int kvm_s390_inject_vm(struct kvm *kvm,
+ struct kvm_s390_interrupt *s390int)
+{
+ struct kvm_s390_interrupt_info *inti;
+ int rc;
+
inti = kzalloc(sizeof(*inti), GFP_KERNEL);
if (!inti)
return -ENOMEM;
@@ -776,39 +867,9 @@ int kvm_s390_inject_vm(struct kvm *kvm,
2);
mutex_lock(&kvm->lock);
- fi = &kvm->arch.float_int;
- spin_lock(&fi->lock);
- if (!is_ioint(inti->type))
- list_add_tail(&inti->list, &fi->list);
- else {
- /* Keep I/O interrupts sorted in isc order. */
- list_for_each_entry(iter, &fi->list, list) {
- if (!is_ioint(iter->type))
- continue;
- if (iter->io.io_int_word <= inti->io.io_int_word)
- continue;
- break;
- }
- list_add_tail(&inti->list, &iter->list);
- }
- atomic_set(&fi->active, 1);
- sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
- if (sigcpu == KVM_MAX_VCPUS) {
- do {
- sigcpu = fi->next_rr_cpu++;
- if (sigcpu == KVM_MAX_VCPUS)
- sigcpu = fi->next_rr_cpu = 0;
- } while (fi->local_int[sigcpu] == NULL);
- }
- li = fi->local_int[sigcpu];
- spin_lock_bh(&li->lock);
- atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
- if (waitqueue_active(&li->wq))
- wake_up_interruptible(&li->wq);
- spin_unlock_bh(&li->lock);
- spin_unlock(&fi->lock);
+ rc = kvm_s390_inject_internal(kvm, inti);
mutex_unlock(&kvm->lock);
- return 0;
+ return rc;
}
int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
new file mode 100644
@@ -0,0 +1,797 @@
+/*
+ * Handling of channel I/O instructions for kvm
+ *
+ * Copyright IBM Corp. 2012
+ *
+ * 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.
+ *
+ * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/types.h>
+#include <asm/cio.h>
+#include <asm/crw.h>
+#include <asm/orb.h>
+#include <asm/schib.h>
+#include <asm/schid.h>
+#include <asm/scsw.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+#include "trace.h"
+
+#define PRIV_CSCH 0x30
+#define PRIV_HSCH 0x31
+#define PRIV_MSCH 0x32
+#define PRIV_SSCH 0x33
+#define PRIV_STSCH 0x34
+#define PRIV_TSCH 0x35
+#define PRIV_TPI 0x36
+#define PRIV_SAL 0x37
+#define PRIV_RSCH 0x38
+#define PRIV_STCRW 0x39
+#define PRIV_STCPS 0x3a
+#define PRIV_RCHP 0x3b
+#define PRIV_SCHM 0x3c
+#define PRIV_CHSC 0x5f
+#define PRIV_XSCH 0x76
+
+static int ioinst_disassemble_sch_ident(u32 value, int *m, int *cssid, int *ssid,
+ int *schid)
+{
+ if (!(value & 0x00010000))
+ return -EINVAL;
+
+ if (!(value & 0x00080000)) {
+ if (value & 0xff000000)
+ return -EINVAL;
+ *m = 0;
+ *cssid = 0;
+ } else {
+ *m = 1;
+ *cssid = (value & 0xff000000) >> 24;
+ }
+ *ssid = (value & 0x00060000) >> 17;
+ *schid = value & 0x0000ffff;
+ return 0;
+}
+
+static int ioinst_handle_xsch(struct kvm_vcpu *vcpu, int *cc, u64 reg1)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ int ret = -ENODEV;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ trace_kvm_s390_handle_ioinst("xsch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch)
+ ret = css_do_xsch(vcpu, sch);
+
+ switch (ret) {
+ case -ENODEV:
+ *cc = 3;
+ break;
+ case -EBUSY:
+ *cc = 2;
+ break;
+ case -EREMOTE:
+ *cc = 0;
+ break;
+ default:
+ *cc = 1;
+ break;
+ }
+
+ return ret;
+}
+
+static int ioinst_handle_csch(struct kvm_vcpu *vcpu, int *cc, u64 reg1)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ int ret = -ENODEV;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ trace_kvm_s390_handle_ioinst("csch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch)
+ ret = css_do_csch(vcpu, sch);
+
+ if (ret == -ENODEV) {
+ *cc = 3;
+ } else {
+ *cc = 0;
+ }
+ return ret;
+}
+
+static int ioinst_handle_hsch(struct kvm_vcpu *vcpu, int *cc, u64 reg1)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ int ret = -ENODEV;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ trace_kvm_s390_handle_ioinst("hsch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch)
+ ret = css_do_hsch(vcpu, sch);
+
+ switch (ret) {
+ case -ENODEV:
+ *cc = 3;
+ break;
+ case -EBUSY:
+ *cc = 2;
+ break;
+ case -EREMOTE:
+ *cc = 0;
+ break;
+ default:
+ *cc = 1;
+ break;
+ }
+
+ return ret;
+}
+
+static int ioinst_schib_valid(struct schib *schib)
+{
+ if (schib->pmcw.res5 != 0)
+ return 0;
+
+ if ((schib->pmcw.unused1 != 0) || (schib->pmcw.unused2 != 0))
+ return 0;
+
+ /* Disallow extended measurements for now. */
+ if (schib->pmcw.xmwme)
+ return 0;
+
+ return 1;
+}
+
+static int ioinst_handle_msch(struct kvm_vcpu *vcpu, int *cc, u64 reg1, u32 ipb)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ struct schib schib;
+ u32 addr;
+ int ret = -ENODEV;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ addr = ipb >> 28;
+ if (addr > 0)
+ addr = vcpu->run->s.regs.gprs[addr];
+
+ addr += (ipb & 0xfff0000) >> 16;
+ if (copy_from_guest(vcpu, &schib, addr, sizeof(struct schib))) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ return -EIO;
+ }
+ if (!ioinst_schib_valid(&schib)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ trace_kvm_s390_handle_ioinst("msch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch)
+ ret = css_do_msch(vcpu, sch, &schib);
+
+ switch (ret) {
+ case -ENODEV:
+ *cc = 3;
+ break;
+ case -EBUSY:
+ *cc = 2;
+ break;
+ case 0:
+ *cc = 0;
+ break;
+ default:
+ *cc = 1;
+ break;
+ }
+
+ return ret;
+}
+
+static int ioinst_orb_valid(union orb *orb)
+{
+ if (orb->cmd.res2 != 0)
+ return 0;
+
+ if (orb->cmd.zero != 0)
+ return 0;
+
+ if ((orb->cmd.cpa & 0x80000000) != 0)
+ return 0;
+
+ return 1;
+}
+
+static int ioinst_handle_ssch(struct kvm_vcpu *vcpu, int *cc, u64 reg1, u32 ipb)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ union orb orb;
+ u32 addr;
+ int ret = -ENODEV;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ addr = ipb >> 28;
+ if (addr > 0)
+ addr = vcpu->run->s.regs.gprs[addr];
+
+ addr += (ipb & 0xfff0000) >> 16;
+ if (copy_from_guest(vcpu, &orb, addr, sizeof(union orb))) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ return -EIO;
+ }
+ if (!ioinst_orb_valid(&orb)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ trace_kvm_s390_handle_ioinst("ssch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch)
+ ret = css_do_ssch(vcpu, sch, addr);
+
+ switch (ret) {
+ case -ENODEV:
+ *cc = 3;
+ break;
+ case -EBUSY:
+ *cc = 2;
+ break;
+ case -EREMOTE:
+ *cc = 0;
+ break;
+ default:
+ *cc = 1;
+ break;
+ }
+
+ return ret;
+}
+
+static int ioinst_handle_stcrw(struct kvm_vcpu *vcpu, int *cc, u32 ipb)
+{
+ int ret;
+ u32 addr;
+
+ addr = ipb >> 28;
+ if (addr > 0)
+ addr = vcpu->run->s.regs.gprs[addr];
+
+ addr += (ipb & 0xfff0000) >> 16;
+ ret = css_do_stcrw(vcpu, addr);
+ /* 0 - crw stored, 1 - zeroes stored */
+ if (ret >= 0) {
+ *cc = ret;
+ ret = 0;
+ }
+ return 0;
+}
+
+static int ioinst_handle_stsch(struct kvm_vcpu *vcpu, int *cc, u64 reg1, u32 ipb)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ u32 addr;
+ int ret;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ addr = ipb >> 28;
+ if (addr > 0)
+ addr = vcpu->run->s.regs.gprs[addr];
+
+ addr += (ipb & 0xfff0000) >> 16;
+ if (addr & 3) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ return -EIO;
+ }
+ trace_kvm_s390_handle_ioinst("stsch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch) {
+ ret = copy_to_guest(vcpu, addr, sch->curr_status,
+ sizeof(*sch->curr_status));
+ if (ret < 0)
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ else
+ *cc = 0;
+ } else {
+ if (css_schid_final(vcpu->kvm, m ? cssid :
+ (cssid ? cssid : VIRTUAL_CSSID),
+ ssid, schid)) {
+ *cc = 3; /* No more subchannels in this css/ss */
+ ret = 0;
+ } else {
+ struct schib schib;
+
+ /* Store an empty schib. */
+ memset(&schib, 0, sizeof(struct schib));
+ ret = copy_to_guest(vcpu, addr, &schib, sizeof(schib));
+ if (ret < 0)
+ kvm_s390_inject_program_int(vcpu,
+ PGM_ADDRESSING);
+ else
+ *cc = 0;
+ }
+ }
+ return ret;
+}
+
+static int ioinst_handle_tsch(struct kvm_vcpu *vcpu, int *cc, u64 reg1, u32 ipb)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ u32 addr;
+ int ret = -ENODEV;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ addr = ipb >> 28;
+ if (addr > 0)
+ addr = vcpu->run->s.regs.gprs[addr];
+
+ addr += (ipb & 0xfff0000) >> 16;
+ trace_kvm_s390_handle_ioinst("tsch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch)
+ ret = css_do_tsch(vcpu, sch, addr);
+ /* 0 - status pending, 1 - not status pending */
+ switch (ret) {
+ case -EBUSY:
+ *cc = 0;
+ break;
+ case 0:
+ *cc = 1;
+ break;
+ case -ENODEV:
+ *cc = 3;
+ break;
+ }
+ return ret;
+}
+
+struct chsc_req {
+ u16 len;
+ u16 command;
+ u32 param0;
+ u32 param1;
+ u32 param2;
+} __attribute__((packed));
+
+struct chsc_resp {
+ u16 len;
+ u16 code;
+ u32 param;
+ char data[0];
+} __attribute__((packed));
+
+#define CHSC_SCPD 0x0002
+#define CHSC_SCSC 0x0010
+#define CHSC_SDA 0x0031
+
+static void ioinst_handle_chsc_scpd(struct kvm *kvm, struct chsc_req *req,
+ struct chsc_resp *res)
+{
+ u16 resp_code;
+ int rfmt;
+ u16 cssid;
+ u8 f_chpid, l_chpid;
+ int desc_size;
+
+ rfmt = (req->param0 & 0x00000f00) >> 8;
+ if ((rfmt == 0) || (rfmt == 1))
+ rfmt = (req->param0 & 0x10000000) >> 28;
+
+ if ((req->len != 0x0010) || (req->param0 & 0xc000f000) ||
+ (req->param1 & 0xffffff00) || req->param2) {
+ resp_code = 0x0003;
+ goto out_err;
+ }
+ if (req->param0 & 0x0f000000) {
+ resp_code = 0x0007;
+ goto out_err;
+ }
+ cssid = (req->param0 & 0x00ff0000) >> 16;
+ if (cssid != 0)
+ if (!(req->param0 & 0x20000000) || (cssid != VIRTUAL_CSSID)) {
+ resp_code = 0x0008;
+ goto out_err;
+ }
+
+ if ((cssid == 0) && (!(req->param0 & 0x20000000)))
+ cssid = VIRTUAL_CSSID;
+
+ f_chpid = req->param0 & 0x000000ff;
+ l_chpid = req->param1 & 0x000000ff;
+ if (l_chpid < f_chpid) {
+ resp_code = 0x0003;
+ goto out_err;
+ }
+ desc_size = css_collect_chp_desc(kvm, cssid, f_chpid, l_chpid, rfmt,
+ &res->data);
+ res->code = 0x0001;
+ res->len = 8 + desc_size;
+ res->param = rfmt;
+ return;
+
+out_err:
+ res->code = resp_code;
+ res->len = 8;
+ res->param = rfmt;
+}
+
+/* For now, always the same characteristics. */
+static u32 general_chars[510] = { 0x03000000, 0x00059000, 0, };
+static u32 chsc_chars[508] = { 0x40000000, 0x00040000, 0, };
+
+static void ioinst_handle_chsc_scsc(struct kvm *kvm, struct chsc_req *req,
+ struct chsc_resp *res)
+{
+ u8 cssid;
+ u16 resp_code;
+
+ if (req->param0 & 0x000f0000) {
+ resp_code = 0x0007;
+ goto out_err;
+ }
+ cssid = (req->param0 & 0x0000ff00) >> 8;
+ if (cssid != 0)
+ if (!(req->param0 & 0x20000000) || (cssid != VIRTUAL_CSSID)) {
+ resp_code = 0x0008;
+ goto out_err;
+ }
+
+ if ((req->param0 & 0xdff000ff) || req->param1 || req->param2) {
+ resp_code = 0x0003;
+ goto out_err;
+ }
+ res->code = 0x0001;
+ res->len = 4080;
+ res->param = 0;
+
+ memcpy(res->data, general_chars, sizeof(general_chars));
+ memcpy(res->data + sizeof(general_chars), chsc_chars,
+ sizeof(chsc_chars));
+ return;
+
+out_err:
+ res->code = resp_code;
+ res->len = 8;
+ res->param = 0;
+}
+
+#define CHSC_SDA_SC_MCSSE 0x0
+#define CHSC_SDA_SC_MSS 0x2
+
+static void ioinst_handle_chsc_sda(struct kvm *kvm, struct chsc_req *req,
+ struct chsc_resp *res)
+{
+ u16 resp_code = 0x0001;
+ u16 oc;
+ int ret;
+
+ if ((req->len != 0x0400) || (req->param0 & 0xf0ff0000)) {
+ resp_code = 0x0003;
+ goto out;
+ }
+
+ if (req->param0 & 0x0f000000) {
+ resp_code = 0x0007;
+ goto out;
+ }
+
+ oc = req->param0 & 0x0000ffff;
+ switch (oc) {
+ case CHSC_SDA_SC_MCSSE:
+ ret = css_enable_mcsse(kvm);
+ if (ret == -EINVAL) {
+ resp_code = 0x0101;
+ goto out;
+ }
+ break;
+ case CHSC_SDA_SC_MSS:
+ ret = css_enable_mss(kvm);
+ if (ret == -EINVAL) {
+ resp_code = 0x0101;
+ goto out;
+ }
+ break;
+ default:
+ resp_code = 0x0003;
+ goto out;
+ }
+
+out:
+ res->code = resp_code;
+ res->len = 8;
+ res->param = 0;
+}
+
+static void ioinst_handle_chsc_unimplemented(struct chsc_resp *res)
+{
+ res->len = 8;
+ res->code = 0x0004;
+ res->param = 0;
+}
+
+static int ioinst_handle_chsc(struct kvm_vcpu *vcpu, int *cc, u32 ipb)
+{
+ struct chsc_req *req;
+ struct chsc_resp *res;
+ u64 addr;
+ int reg;
+ int ret;
+
+ reg = (ipb >> 20) & 0x00f;
+ addr = vcpu->run->s.regs.gprs[reg];
+ if (addr & 0x0000000000000fff) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ return -EIO;
+ }
+ req = (struct chsc_req *)get_zeroed_page(GFP_KERNEL);
+ if (!req)
+ return -EFAULT;
+ if (copy_from_guest(vcpu, req, addr, sizeof(*req))) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ return -EFAULT;
+ }
+ if ((req->len & 3) || (req->len < 16) || (req->len > 4088)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ res = (struct chsc_resp *)((unsigned long)req + req->len);
+ switch (req->command) {
+ case CHSC_SCSC:
+ ioinst_handle_chsc_scsc(vcpu->kvm, req, res);
+ break;
+ case CHSC_SCPD:
+ ioinst_handle_chsc_scpd(vcpu->kvm, req, res);
+ break;
+ case CHSC_SDA:
+ ioinst_handle_chsc_sda(vcpu->kvm, req, res);
+ break;
+ default:
+ ioinst_handle_chsc_unimplemented(res);
+ break;
+ }
+ ret = copy_to_guest(vcpu, addr + req->len, res, res->len);
+ if (ret < 0)
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ else
+ *cc = 0;
+ free_page((unsigned long)req);
+ return ret;
+}
+
+static int ioinst_handle_tpi(struct kvm_vcpu *vcpu, int *cc, u32 ipb)
+{
+ u32 addr;
+ int lowcore;
+
+ addr = ipb >> 28;
+ if (addr > 0)
+ addr = vcpu->run->s.regs.gprs[addr];
+
+ addr += (ipb & 0xfff0000) >> 16;
+ lowcore = addr ? 0 : 1;
+ *cc = css_do_tpi(vcpu, addr, lowcore);
+ return 0;
+}
+
+static int ioinst_handle_schm(struct kvm_vcpu *vcpu, u64 reg1, u64 reg2,
+ u32 ipb)
+{
+ u8 mbk;
+ int update;
+ int dct;
+
+ if (reg1 & 0x000000000ffffffc) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+
+ mbk = (reg1 & 0x00000000f0000000) >> 28;
+ update = (reg1 & 0x0000000000000002) >> 1;
+ dct = reg1 & 0x0000000000000001;
+
+ if (update && (reg2 & 0x0000000000000fff)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+
+ css_do_schm(vcpu, mbk, update, dct, update ? reg2 : 0);
+
+ return 0;
+}
+
+static int ioinst_handle_rsch(struct kvm_vcpu *vcpu, int *cc, u64 reg1)
+{
+ int m, cssid, ssid, schid;
+ struct kvm_subch *sch;
+ int ret = -ENODEV;
+
+ if (ioinst_disassemble_sch_ident(reg1, &m, &cssid, &ssid, &schid)) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ trace_kvm_s390_handle_ioinst("rsch", cssid, ssid, schid);
+ sch = css_find_subch(vcpu->kvm, m, cssid, ssid, schid);
+ if (sch)
+ ret = css_do_rsch(vcpu, sch);
+
+ switch (ret) {
+ case -ENODEV:
+ *cc = 3;
+ break;
+ case -EINVAL:
+ *cc = 2;
+ break;
+ case -EREMOTE:
+ *cc = 0;
+ break;
+ default:
+ *cc = 1;
+ break;
+ }
+
+ return ret;
+
+}
+
+static int ioinst_handle_rchp(struct kvm_vcpu *vcpu, int *cc, u64 reg1)
+{
+ u8 cssid;
+ u8 chpid;
+ int ret;
+ struct kvm_s390_css_data *css = vcpu->kvm->arch.css;
+
+ if (reg1 & 0xff00ff00) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+
+ cssid = (reg1 >> 16) & 0xff;
+ chpid = reg1 & 0xff;
+
+ if (cssid > css->max_cssid) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ ret = -EIO;
+ } else if (!css_chpid_in_use(vcpu->kvm, cssid, chpid)) {
+ ret = 0;
+ *cc = 3;
+ } else {
+ /*
+ * Since we only support virtual (i.e. not real) channel paths,
+ * there's nothing left for us to do save signaling success.
+ */
+ css_queue_crw(vcpu->kvm, CRW_RSC_CPATH, CRW_ERC_INIT,
+ css->max_cssid > 0 ? 1 : 0, chpid);
+ if (css->max_cssid > 0)
+ css_queue_crw(vcpu->kvm, CRW_RSC_CPATH, CRW_ERC_INIT, 0,
+ cssid << 8);
+ ret = 0;
+ *cc = 0;
+ }
+
+ return ret;
+}
+
+static int ioinst_handle_sal(struct kvm_vcpu *vcpu, u64 reg1)
+{
+ /* We do not provide address limit checking, so let's suppress it. */
+ if (reg1 & 0x000000008000ffff) {
+ kvm_s390_inject_program_int(vcpu, PGM_OPERAND);
+ return -EIO;
+ }
+ return 0;
+}
+
+int kvm_css_instruction(struct kvm_vcpu *vcpu)
+{
+ int ret;
+ int cc;
+ int no_cc = 0;
+
+ if ((vcpu->arch.sie_block->ipa & 0xff00) != 0xb200)
+ /* Not handled for now. */
+ return -EOPNOTSUPP;
+
+ switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+ case PRIV_XSCH:
+ ret = ioinst_handle_xsch(vcpu, &cc, vcpu->run->s.regs.gprs[1]);
+ break;
+ case PRIV_CSCH:
+ ret = ioinst_handle_csch(vcpu, &cc, vcpu->run->s.regs.gprs[1]);
+ break;
+ case PRIV_HSCH:
+ ret = ioinst_handle_hsch(vcpu, &cc, vcpu->run->s.regs.gprs[1]);
+ break;
+ case PRIV_MSCH:
+ ret = ioinst_handle_msch(vcpu, &cc, vcpu->run->s.regs.gprs[1],
+ vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_SSCH:
+ ret = ioinst_handle_ssch(vcpu, &cc, vcpu->run->s.regs.gprs[1],
+ vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_STCRW:
+ ret = ioinst_handle_stcrw(vcpu, &cc, vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_STSCH:
+ ret = ioinst_handle_stsch(vcpu, &cc, vcpu->run->s.regs.gprs[1],
+ vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_TSCH:
+ ret = ioinst_handle_tsch(vcpu, &cc, vcpu->run->s.regs.gprs[1],
+ vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_CHSC:
+ ret = ioinst_handle_chsc(vcpu, &cc, vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_TPI:
+ ret = ioinst_handle_tpi(vcpu, &cc, vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_SCHM:
+ no_cc = 1;
+ ret = ioinst_handle_schm(vcpu, vcpu->run->s.regs.gprs[1],
+ vcpu->run->s.regs.gprs[2],
+ vcpu->arch.sie_block->ipb);
+ break;
+ case PRIV_RSCH:
+ ret = ioinst_handle_rsch(vcpu, &cc, vcpu->run->s.regs.gprs[1]);
+ break;
+ case PRIV_RCHP:
+ ret = ioinst_handle_rchp(vcpu, &cc, vcpu->run->s.regs.gprs[1]);
+ break;
+ case PRIV_STCPS:
+ /* We do not provide this instruction, it is suppressed. */
+ no_cc = 1;
+ ret = 0;
+ break;
+ case PRIV_SAL:
+ no_cc = 1;
+ ret = ioinst_handle_sal(vcpu, vcpu->run->s.regs.gprs[1]);
+ break;
+ default:
+ /* Give user space a go at this. */
+ return -EOPNOTSUPP;
+ }
+ if ((ret != -EFAULT) && (ret != -EIO) && (ret != -EREMOTE))
+ ret = 0;
+
+ if ((!ret || (ret == -EREMOTE)) && !no_cc) {
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44;
+ }
+
+ return (ret == -EREMOTE) ? ret : 0;
+}
@@ -141,6 +141,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_SYNC_REGS:
case KVM_CAP_ONE_REG:
case KVM_CAP_ENABLE_CAP:
+ case KVM_CAP_S390_CSS_SUPPORT:
r = 1;
break;
case KVM_CAP_NR_VCPUS:
@@ -183,6 +184,24 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_s390_inject_vm(kvm, &s390int);
break;
}
+ case KVM_S390_CCW_HOTPLUG: {
+ struct kvm_s390_sch_info sch_info;
+
+ r = -EFAULT;
+ if (copy_from_user(&sch_info, argp, sizeof(sch_info)))
+ break;
+ r = kvm_s390_process_ccw_hotplug(kvm, &sch_info);
+ break;
+ }
+ case KVM_S390_CHP_HOTPLUG: {
+ struct kvm_s390_chp_info chp_info;
+
+ r = -EFAULT;
+ if (copy_from_user(&chp_info, argp, sizeof(chp_info)))
+ break;
+ r = kvm_s390_process_chp_hotplug(kvm, &chp_info);
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -235,6 +254,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (!kvm->arch.gmap)
goto out_nogmap;
}
+
+ kvm->arch.css_support = 0;
+
return 0;
out_nogmap:
debug_unregister(kvm->arch.dbf);
@@ -657,6 +679,7 @@ rerun_vcpu:
case KVM_EXIT_INTR:
case KVM_EXIT_S390_RESET:
case KVM_EXIT_S390_UCONTROL:
+ case KVM_EXIT_S390_SCH_IO:
break;
default:
BUG();
@@ -817,6 +840,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
return -EINVAL;
switch (cap->cap) {
+ case KVM_CAP_S390_CSS_SUPPORT:
+ r = kvm_s390_enable_css(vcpu->kvm);
+ break;
default:
r = -EINVAL;
break;
@@ -919,6 +945,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
break;
}
+ case KVM_S390_CSS_NOTIFY:
+ {
+ struct kvm_css_notify notify;
+ r = -EFAULT;
+ if (copy_from_user(¬ify, argp, sizeof(notify)))
+ break;
+ r = kvm_arch_vcpu_ioctl_css_notify(vcpu, ¬ify);
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -76,6 +76,11 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
struct kvm_s390_interrupt *s390int);
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
+int kvm_s390_inject_internal(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti);
+int kvm_s390_dequeue_internal(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti);
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, u64 cr6);
/* implemented in priv.c */
int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
@@ -94,4 +99,37 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu,
/* implemented in diag.c */
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
+/* implemented in ioinst.c */
+int kvm_css_instruction(struct kvm_vcpu *vcpu);
+
+/* implemented in css.c */
+struct schib;
+int kvm_arch_vcpu_ioctl_css_notify(struct kvm_vcpu *vcpu,
+ struct kvm_css_notify *notify);
+int kvm_s390_process_ccw_hotplug(struct kvm *kvm,
+ struct kvm_s390_sch_info *sch_info);
+int kvm_s390_process_chp_hotplug(struct kvm *kvm,
+ struct kvm_s390_chp_info *chp_info);
+int kvm_s390_enable_css(struct kvm *kvm);
+struct kvm_subch *css_find_subch(struct kvm *kvm, u8 m, u8 cssid, u8 ssid,
+ u16 schid);
+int css_do_stsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch, u32 addr);
+int css_schid_final(struct kvm *kvm, u8 cssid, u8 ssid, u16 schid);
+int css_do_msch(struct kvm_vcpu *vcpu, struct kvm_subch *sch, struct schib *schib);
+int css_do_xsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch);
+int css_do_csch(struct kvm_vcpu *vcpu, struct kvm_subch *sch);
+int css_do_hsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch);
+int css_do_ssch(struct kvm_vcpu *vcpu, struct kvm_subch *sch, u64 orb);
+int css_do_tsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch, u32 addr);
+int css_do_stcrw(struct kvm_vcpu *vcpu, u32 addr);
+int css_do_tpi(struct kvm_vcpu *vcpu, u32 addr, int lowcore);
+int css_collect_chp_desc(struct kvm *kvm, u8 cssid, u8 f_chpid, u8 l_chpid,
+ int rfmt, void *buf);
+void css_do_schm(struct kvm_vcpu *vcpu, u8 mbk, int update, int dct, uint64_t mbo);
+int css_enable_mcsse(struct kvm *kvm);
+int css_enable_mss(struct kvm *kvm);
+int css_do_rsch(struct kvm_vcpu *vcpu, struct kvm_subch *sch);
+int css_do_rchp(struct kvm_vcpu *vcpu, u8 cssid, u8 chpid);
+int css_chpid_in_use(struct kvm *kvm, u8 cssid, u8 chpid);
+void css_queue_crw(struct kvm *kvm, u8 rsc, u8 erc, int chain, u16 rsid);
#endif
@@ -138,7 +138,12 @@ static int handle_skey(struct kvm_vcpu *vcpu)
static int handle_io_inst(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 4, "%s", "I/O instruction");
- /* condition code 3 */
+
+ if (vcpu->kvm->arch.css_support)
+ /* Use in-kernel css support. */
+ return kvm_css_instruction(vcpu);
+
+ /* Set cc 3 to stop guest issueing I/O instructions. */
vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
return 0;
@@ -203,6 +203,73 @@ TRACE_EVENT(kvm_s390_stop_request,
__entry->action_bits)
);
+/*
+ * Trace point for enabling in-kernel channel subsystem support.
+ */
+TRACE_EVENT(kvm_s390_enable_kernel_css,
+ TP_PROTO(void *kvm),
+ TP_ARGS(kvm),
+
+ TP_STRUCT__entry(
+ __field(void *, kvm)
+ ),
+
+ TP_fast_assign(
+ __entry->kvm = kvm;
+ ),
+
+ TP_printk("enabling in-kernel css support (kvm @ %p)\n",
+ __entry->kvm)
+ );
+
+/*
+ * Trace point for user space subchannel I/O notification.
+ */
+TRACE_EVENT(kvm_s390_css_notify,
+ TP_PROTO(u8 cssid, u8 ssid, u16 schid),
+ TP_ARGS(cssid, ssid, schid),
+
+ TP_STRUCT__entry(
+ __field(u8, cssid)
+ __field(u8, ssid)
+ __field(u16, schid)
+ ),
+
+ TP_fast_assign(
+ __entry->cssid = cssid;
+ __entry->ssid = ssid;
+ __entry->schid = schid;
+ ),
+
+ TP_printk("css notification for subchannel %x.%x.%04x\n",
+ __entry->cssid, __entry->ssid, __entry->schid)
+ );
+
+/*
+ * Trace point for user space subchannel hotplug notification.
+ */
+TRACE_EVENT(kvm_s390_ccw_hotplug,
+ TP_PROTO(u8 cssid, u8 ssid, u16 schid, int add),
+ TP_ARGS(cssid, ssid, schid, add),
+
+ TP_STRUCT__entry(
+ __field(u8, cssid)
+ __field(u8, ssid)
+ __field(u16, schid)
+ __field(int, add)
+ ),
+
+ TP_fast_assign(
+ __entry->cssid = cssid;
+ __entry->ssid = ssid;
+ __entry->schid = schid;
+ __entry->add = add;
+ ),
+
+ TP_printk("hotplug event for subchannel %x.%x.%04x (%s)\n",
+ __entry->cssid, __entry->ssid, __entry->schid,
+ __entry->add ? "attach" : "detach")
+ );
#endif /* _TRACE_KVMS390_H */
@@ -335,6 +335,28 @@ TRACE_EVENT(kvm_s390_handle_stsi,
__entry->addr)
);
+TRACE_EVENT(kvm_s390_handle_ioinst,
+ TP_PROTO(char *name, u8 cssid, u8 ssid, u16 schid),
+ TP_ARGS(name, cssid, ssid, schid),
+
+ TP_STRUCT__entry(
+ __field(char *, name)
+ __field(u8, cssid)
+ __field(u8, ssid)
+ __field(u16, schid)
+ ),
+
+ TP_fast_assign(
+ __entry->name = name;
+ __entry->cssid = cssid;
+ __entry->ssid = ssid;
+ __entry->schid = schid;
+ ),
+
+ TP_printk("I/O instruction %s (%x.%x.%04x)", __entry->name,
+ __entry->cssid, __entry->ssid, __entry->schid)
+ );
+
#endif /* _TRACE_KVM_H */
/* This part must be outside protection */
@@ -163,6 +163,7 @@ struct kvm_pit_config {
#define KVM_EXIT_OSI 18
#define KVM_EXIT_PAPR_HCALL 19
#define KVM_EXIT_S390_UCONTROL 20
+#define KVM_EXIT_S390_SCH_IO 21
/* For KVM_EXIT_INTERNAL_ERROR */
#define KVM_INTERNAL_ERROR_EMULATION 1
@@ -276,6 +277,20 @@ struct kvm_run {
__u64 ret;
__u64 args[9];
} papr_hcall;
+ /* KVM_EXIT_S390_SCH_IO */
+ struct {
+ __u32 sch_id;
+#define SCH_DO_CSCH 0
+#define SCH_DO_HSCH 1
+#define SCH_DO_SSCH 2
+#define SCH_DO_RSCH 3
+#define SCH_DO_XSCH 4
+ __u8 func;
+ __u8 pad;
+ __u64 orb;
+ __u32 scsw[3];
+ __u32 pmcw[7];
+ } s390_sch_io;
/* Fix the size of the union. */
char padding[256];
};
@@ -480,6 +495,39 @@ struct kvm_ppc_smmu_info {
struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
};
+/* for KVM_S390_CSS_NOTIFY */
+struct kvm_css_notify {
+ __u8 cssid;
+ __u8 ssid;
+ __u16 schid;
+ __u32 scsw[3];
+ __u32 pmcw[7];
+ __u8 sense_data[32];
+ __u8 unsolicited;
+ __u8 func;
+};
+
+/* for KVM_S390_CCW_HOTPLUG */
+struct kvm_s390_sch_info {
+ __u8 cssid;
+ __u8 ssid;
+ __u16 schid;
+ __u16 devno;
+ __u32 schib[12];
+ int hotplugged;
+ int add;
+ int virtual;
+};
+
+/* for KVM_S390_CHP_HOTPLUG */
+struct kvm_s390_chp_info {
+ __u8 cssid;
+ __u8 chpid;
+ __u8 type;
+ int add;
+ int virtual;
+};
+
#define KVMIO 0xAE
/* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -625,6 +673,7 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_PPC_GET_SMMU_INFO 78
#define KVM_CAP_S390_COW 79
#define KVM_CAP_PPC_ALLOC_HTAB 80
+#define KVM_CAP_S390_CSS_SUPPORT 81
#ifdef KVM_CAP_IRQ_ROUTING
@@ -838,6 +887,10 @@ struct kvm_s390_ucas_mapping {
#define KVM_PPC_GET_SMMU_INFO _IOR(KVMIO, 0xa6, struct kvm_ppc_smmu_info)
/* Available with KVM_CAP_PPC_ALLOC_HTAB */
#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32)
+/* Available with KVM_CAP_S390_CSS_SUPPORT */
+#define KVM_S390_CSS_NOTIFY _IOW(KVMIO, 0xae, struct kvm_css_notify)
+#define KVM_S390_CCW_HOTPLUG _IOW(KVMIO, 0xab, struct kvm_s390_sch_info)
+#define KVM_S390_CHP_HOTPLUG _IOW(KVMIO, 0xac, struct kvm_s390_chp_info)
/*
* ioctls for vcpu fds
@@ -14,7 +14,7 @@
ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR), \
ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\
ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL), \
- ERSN(S390_UCONTROL)
+ ERSN(S390_UCONTROL), ERSN(S390_SCH_IO)
TRACE_EVENT(kvm_userspace_exit,
TP_PROTO(__u32 reason, int errno),
@@ -1817,7 +1817,8 @@ static long kvm_vcpu_ioctl(struct file *filp,
* Special cases: vcpu ioctls that are asynchronous to vcpu execution,
* so vcpu_load() would break it.
*/
- if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_INTERRUPT)
+ if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_INTERRUPT ||
+ ioctl == KVM_S390_CSS_NOTIFY)
return kvm_arch_vcpu_ioctl(filp, ioctl, arg);
#endif
Handle most support for channel I/O instructions in the kernel itself. Only asynchronous functions (such as the start function) need to be handled by userspace. Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com> --- Documentation/virtual/kvm/api.txt | 127 +++++ arch/s390/include/asm/kvm_host.h | 48 ++ arch/s390/kvm/Makefile | 2 +- arch/s390/kvm/css.c | 945 ++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/intercept.c | 1 + arch/s390/kvm/interrupt.c | 147 ++++-- arch/s390/kvm/ioinst.c | 797 ++++++++++++++++++++++++++++++++ arch/s390/kvm/kvm-s390.c | 35 ++ arch/s390/kvm/kvm-s390.h | 38 ++ arch/s390/kvm/priv.c | 7 +- arch/s390/kvm/trace-s390.h | 67 +++ arch/s390/kvm/trace.h | 22 + include/linux/kvm.h | 53 +++ include/trace/events/kvm.h | 2 +- virt/kvm/kvm_main.c | 3 +- 15 files changed, 2247 insertions(+), 47 deletions(-) create mode 100644 arch/s390/kvm/css.c create mode 100644 arch/s390/kvm/ioinst.c