summaryrefslogtreecommitdiffstats
path: root/arch/s390/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/kvm')
-rw-r--r--arch/s390/kvm/Kconfig1
-rw-r--r--arch/s390/kvm/Makefile2
-rw-r--r--arch/s390/kvm/diag.c12
-rw-r--r--arch/s390/kvm/gaccess.c95
-rw-r--r--arch/s390/kvm/gaccess.h38
-rw-r--r--arch/s390/kvm/guestdbg.c8
-rw-r--r--arch/s390/kvm/intercept.c85
-rw-r--r--arch/s390/kvm/interrupt.c242
-rw-r--r--arch/s390/kvm/kvm-s390.c661
-rw-r--r--arch/s390/kvm/kvm-s390.h35
-rw-r--r--arch/s390/kvm/priv.c20
-rw-r--r--arch/s390/kvm/sigp.c8
-rw-r--r--arch/s390/kvm/trace-s390.h6
13 files changed, 806 insertions, 407 deletions
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 5fce52cf0e57..5ea5af3c7db7 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select SRCU
+ select KVM_VFIO
---help---
Support hosting paravirtualized guest machines using the SIE
virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index b3b553469650..d42fa38c2429 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -7,7 +7,7 @@
# as published by the Free Software Foundation.
KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 5fbfb88f8477..1ea4095b67d7 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -14,6 +14,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/pgalloc.h>
+#include <asm/gmap.h>
#include <asm/virtio-ccw.h>
#include "kvm-s390.h"
#include "trace.h"
@@ -155,10 +156,8 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
{
- struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tcpu;
int tid;
- int i;
tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
vcpu->stat.diagnose_9c++;
@@ -167,12 +166,9 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
if (tid == vcpu->vcpu_id)
return 0;
- kvm_for_each_vcpu(i, tcpu, kvm)
- if (tcpu->vcpu_id == tid) {
- kvm_vcpu_yield_to(tcpu);
- break;
- }
-
+ tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
+ if (tcpu)
+ kvm_vcpu_yield_to(tcpu);
return 0;
}
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index a7559f7207df..66938d283b77 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -259,10 +259,14 @@ struct aste {
int ipte_lock_held(struct kvm_vcpu *vcpu)
{
- union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control;
+ if (vcpu->arch.sie_block->eca & 1) {
+ int rc;
- if (vcpu->arch.sie_block->eca & 1)
- return ic->kh != 0;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0;
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+ return rc;
+ }
return vcpu->kvm->arch.ipte_lock_count != 0;
}
@@ -274,16 +278,20 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu)
vcpu->kvm->arch.ipte_lock_count++;
if (vcpu->kvm->arch.ipte_lock_count > 1)
goto out;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
- while (old.k) {
+ if (old.k) {
+ read_unlock(&vcpu->kvm->arch.sca_lock);
cond_resched();
- old = READ_ONCE(*ic);
+ goto retry;
}
new = old;
new.k = 1;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
out:
mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
}
@@ -296,12 +304,14 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
vcpu->kvm->arch.ipte_lock_count--;
if (vcpu->kvm->arch.ipte_lock_count)
goto out;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
new = old;
new.k = 0;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
wake_up(&vcpu->kvm->arch.ipte_wq);
out:
mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
@@ -311,24 +321,29 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
- while (old.kg) {
+ if (old.kg) {
+ read_unlock(&vcpu->kvm->arch.sca_lock);
cond_resched();
- old = READ_ONCE(*ic);
+ goto retry;
}
new = old;
new.k = 1;
new.kh++;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
}
static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
new = old;
@@ -336,6 +351,7 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
if (!new.kh)
new.k = 0;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
if (!new.kh)
wake_up(&vcpu->kvm->arch.ipte_wq);
}
@@ -357,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu)
}
static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
- int write)
+ enum gacc_mode mode)
{
union alet alet;
struct ale ale;
@@ -438,7 +454,7 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
}
}
- if (ale.fo == 1 && write)
+ if (ale.fo == 1 && mode == GACC_STORE)
return PGM_PROTECTION;
asce->val = aste.asce;
@@ -461,25 +477,28 @@ enum {
};
static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
- ar_t ar, int write)
+ ar_t ar, enum gacc_mode mode)
{
int rc;
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
+ struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
struct trans_exc_code_bits *tec_bits;
memset(pgm, 0, sizeof(*pgm));
tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
- tec_bits->fsi = write ? FSI_STORE : FSI_FETCH;
- tec_bits->as = psw_bits(*psw).as;
+ tec_bits->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH;
+ tec_bits->as = psw.as;
- if (!psw_bits(*psw).t) {
+ if (!psw.t) {
asce->val = 0;
asce->r = 1;
return 0;
}
- switch (psw_bits(vcpu->arch.sie_block->gpsw).as) {
+ if (mode == GACC_IFETCH)
+ psw.as = psw.as == PSW_AS_HOME ? PSW_AS_HOME : PSW_AS_PRIMARY;
+
+ switch (psw.as) {
case PSW_AS_PRIMARY:
asce->val = vcpu->arch.sie_block->gcr[1];
return 0;
@@ -490,7 +509,7 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
asce->val = vcpu->arch.sie_block->gcr[13];
return 0;
case PSW_AS_ACCREG:
- rc = ar_translation(vcpu, asce, ar, write);
+ rc = ar_translation(vcpu, asce, ar, mode);
switch (rc) {
case PGM_ALEN_TRANSLATION:
case PGM_ALE_SEQUENCE:
@@ -522,7 +541,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
* @gva: guest virtual address
* @gpa: points to where guest physical (absolute) address should be stored
* @asce: effective asce
- * @write: indicates if access is a write access
+ * @mode: indicates the access mode to be used
*
* Translate a guest virtual address into a guest absolute address by means
* of dynamic address translation as specified by the architecture.
@@ -538,7 +557,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
*/
static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
unsigned long *gpa, const union asce asce,
- int write)
+ enum gacc_mode mode)
{
union vaddress vaddr = {.addr = gva};
union raddress raddr = {.addr = gva};
@@ -683,7 +702,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
real_address:
raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr);
absolute_address:
- if (write && dat_protection)
+ if (mode == GACC_STORE && dat_protection)
return PGM_PROTECTION;
if (kvm_is_error_gpa(vcpu->kvm, raddr.addr))
return PGM_ADDRESSING;
@@ -712,7 +731,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
unsigned long *pages, unsigned long nr_pages,
- const union asce asce, int write)
+ const union asce asce, enum gacc_mode mode)
{
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -724,13 +743,13 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
while (nr_pages) {
ga = kvm_s390_logical_to_effective(vcpu, ga);
tec_bits->addr = ga >> PAGE_SHIFT;
- if (write && lap_enabled && is_low_address(ga)) {
+ if (mode == GACC_STORE && lap_enabled && is_low_address(ga)) {
pgm->code = PGM_PROTECTION;
return pgm->code;
}
ga &= PAGE_MASK;
if (psw_bits(*psw).t) {
- rc = guest_translate(vcpu, ga, pages, asce, write);
+ rc = guest_translate(vcpu, ga, pages, asce, mode);
if (rc < 0)
return rc;
if (rc == PGM_PROTECTION)
@@ -752,7 +771,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
}
int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
- unsigned long len, int write)
+ unsigned long len, enum gacc_mode mode)
{
psw_t *psw = &vcpu->arch.sie_block->gpsw;
unsigned long _len, nr_pages, gpa, idx;
@@ -764,7 +783,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
if (!len)
return 0;
- rc = get_vcpu_asce(vcpu, &asce, ar, write);
+ rc = get_vcpu_asce(vcpu, &asce, ar, mode);
if (rc)
return rc;
nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
@@ -776,11 +795,11 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
need_ipte_lock = psw_bits(*psw).t && !asce.r;
if (need_ipte_lock)
ipte_lock(vcpu);
- rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write);
+ rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, mode);
for (idx = 0; idx < nr_pages && !rc; idx++) {
gpa = *(pages + idx) + (ga & ~PAGE_MASK);
_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
- if (write)
+ if (mode == GACC_STORE)
rc = kvm_write_guest(vcpu->kvm, gpa, data, _len);
else
rc = kvm_read_guest(vcpu->kvm, gpa, data, _len);
@@ -796,7 +815,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
}
int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
- void *data, unsigned long len, int write)
+ void *data, unsigned long len, enum gacc_mode mode)
{
unsigned long _len, gpa;
int rc = 0;
@@ -804,7 +823,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
while (len && !rc) {
gpa = kvm_s390_real_to_abs(vcpu, gra);
_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
- if (write)
+ if (mode)
rc = write_guest_abs(vcpu, gpa, data, _len);
else
rc = read_guest_abs(vcpu, gpa, data, _len);
@@ -825,7 +844,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
* has to take care of this.
*/
int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
- unsigned long *gpa, int write)
+ unsigned long *gpa, enum gacc_mode mode)
{
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -835,19 +854,19 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
gva = kvm_s390_logical_to_effective(vcpu, gva);
tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
- rc = get_vcpu_asce(vcpu, &asce, ar, write);
+ rc = get_vcpu_asce(vcpu, &asce, ar, mode);
tec->addr = gva >> PAGE_SHIFT;
if (rc)
return rc;
if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
- if (write) {
+ if (mode == GACC_STORE) {
rc = pgm->code = PGM_PROTECTION;
return rc;
}
}
if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */
- rc = guest_translate(vcpu, gva, gpa, asce, write);
+ rc = guest_translate(vcpu, gva, gpa, asce, mode);
if (rc > 0) {
if (rc == PGM_PROTECTION)
tec->b61 = 1;
@@ -867,7 +886,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
* check_gva_range - test a range of guest virtual addresses for accessibility
*/
int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
- unsigned long length, int is_write)
+ unsigned long length, enum gacc_mode mode)
{
unsigned long gpa;
unsigned long currlen;
@@ -876,7 +895,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
ipte_lock(vcpu);
while (length > 0 && !rc) {
currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE));
- rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write);
+ rc = guest_translate_address(vcpu, gva, ar, &gpa, mode);
gva += currlen;
length -= currlen;
}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index ef03726cc661..df0a79dd8159 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -155,16 +155,22 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
return kvm_read_guest(vcpu->kvm, gpa, data, len);
}
+enum gacc_mode {
+ GACC_FETCH,
+ GACC_STORE,
+ GACC_IFETCH,
+};
+
int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
- ar_t ar, unsigned long *gpa, int write);
+ ar_t ar, unsigned long *gpa, enum gacc_mode mode);
int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
- unsigned long length, int is_write);
+ unsigned long length, enum gacc_mode mode);
int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
- unsigned long len, int write);
+ unsigned long len, enum gacc_mode mode);
int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
- void *data, unsigned long len, int write);
+ void *data, unsigned long len, enum gacc_mode mode);
/**
* write_guest - copy data from kernel space to guest space
@@ -215,7 +221,7 @@ static inline __must_check
int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len)
{
- return access_guest(vcpu, ga, ar, data, len, 1);
+ return access_guest(vcpu, ga, ar, data, len, GACC_STORE);
}
/**
@@ -235,7 +241,27 @@ static inline __must_check
int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len)
{
- return access_guest(vcpu, ga, ar, data, len, 0);
+ return access_guest(vcpu, ga, ar, data, len, GACC_FETCH);
+}
+
+/**
+ * read_guest_instr - copy instruction data from guest space to kernel space
+ * @vcpu: virtual cpu
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from the current psw address (guest space) to @data (kernel
+ * space).
+ *
+ * The behaviour of read_guest_instr is identical to read_guest, except that
+ * instruction data will be read from primary space when in home-space or
+ * address-space mode.
+ */
+static inline __must_check
+int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len)
+{
+ return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len,
+ GACC_IFETCH);
}
/**
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 47518a324d75..e8c6843b9600 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -17,7 +17,7 @@
/*
* Extends the address range given by *start and *stop to include the address
* range starting with estart and the length len. Takes care of overflowing
- * intervals and tries to minimize the overall intervall size.
+ * intervals and tries to minimize the overall interval size.
*/
static void extend_address_range(u64 *start, u64 *stop, u64 estart, int len)
{
@@ -72,7 +72,7 @@ static void enable_all_hw_bp(struct kvm_vcpu *vcpu)
return;
/*
- * If the guest is not interrested in branching events, we can savely
+ * If the guest is not interested in branching events, we can safely
* limit them to the PER address range.
*/
if (!(*cr9 & PER_EVENT_BRANCH))
@@ -116,7 +116,7 @@ static void enable_all_hw_wp(struct kvm_vcpu *vcpu)
if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) {
*cr9 &= ~PER_CONTROL_ALTERATION;
*cr10 = 0;
- *cr11 = PSW_ADDR_INSN;
+ *cr11 = -1UL;
} else {
*cr9 &= ~PER_CONTROL_ALTERATION;
*cr9 |= PER_EVENT_STORE;
@@ -159,7 +159,7 @@ void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->gcr[0] &= ~0x800ul;
vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH;
vcpu->arch.sie_block->gcr[10] = 0;
- vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN;
+ vcpu->arch.sie_block->gcr[11] = -1UL;
}
if (guestdbg_hw_bp_enabled(vcpu)) {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index b4a5aa110cec..2e6b54e4d3f9 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -38,25 +38,37 @@ static const intercept_handler_t instruction_handlers[256] = {
[0xeb] = kvm_s390_handle_eb,
};
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
{
struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+ u8 ilen = 0;
- /* Use the length of the EXECUTE instruction if necessary */
- if (sie_block->icptstatus & 1) {
- ilc = (sie_block->icptstatus >> 4) & 0x6;
- if (!ilc)
- ilc = 4;
+ switch (vcpu->arch.sie_block->icptcode) {
+ case ICPT_INST:
+ case ICPT_INSTPROGI:
+ case ICPT_OPEREXC:
+ case ICPT_PARTEXEC:
+ case ICPT_IOINST:
+ /* instruction only stored for these icptcodes */
+ ilen = insn_length(vcpu->arch.sie_block->ipa >> 8);
+ /* Use the length of the EXECUTE instruction if necessary */
+ if (sie_block->icptstatus & 1) {
+ ilen = (sie_block->icptstatus >> 4) & 0x6;
+ if (!ilen)
+ ilen = 4;
+ }
+ break;
+ case ICPT_PROGI:
+ /* bit 1+2 of pgmilc are the ilc, so we directly get ilen */
+ ilen = vcpu->arch.sie_block->pgmilc & 0x6;
+ break;
}
- sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc);
+ return ilen;
}
static int handle_noop(struct kvm_vcpu *vcpu)
{
switch (vcpu->arch.sie_block->icptcode) {
- case 0x0:
- vcpu->stat.exit_null++;
- break;
case 0x10:
vcpu->stat.exit_external_request++;
break;
@@ -124,11 +136,13 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
}
-static void __extract_prog_irq(struct kvm_vcpu *vcpu,
- struct kvm_s390_pgm_info *pgm_info)
+static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu)
{
- memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info));
- pgm_info->code = vcpu->arch.sie_block->iprcc;
+ struct kvm_s390_pgm_info pgm_info = {
+ .code = vcpu->arch.sie_block->iprcc,
+ /* the PSW has already been rewound */
+ .flags = KVM_S390_PGM_FLAGS_NO_REWIND,
+ };
switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) {
case PGM_AFX_TRANSLATION:
@@ -141,7 +155,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
case PGM_PRIMARY_AUTHORITY:
case PGM_SECONDARY_AUTHORITY:
case PGM_SPACE_SWITCH:
- pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
break;
case PGM_ALEN_TRANSLATION:
case PGM_ALE_SEQUENCE:
@@ -149,7 +163,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
case PGM_ASTE_SEQUENCE:
case PGM_ASTE_VALIDITY:
case PGM_EXTENDED_AUTHORITY:
- pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+ pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
break;
case PGM_ASCE_TYPE:
case PGM_PAGE_TRANSLATION:
@@ -157,32 +171,33 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
case PGM_REGION_SECOND_TRANS:
case PGM_REGION_THIRD_TRANS:
case PGM_SEGMENT_TRANSLATION:
- pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
- pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
- pgm_info->op_access_id = vcpu->arch.sie_block->oai;
+ pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
+ pgm_info.op_access_id = vcpu->arch.sie_block->oai;
break;
case PGM_MONITOR:
- pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn;
- pgm_info->mon_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.mon_class_nr = vcpu->arch.sie_block->mcn;
+ pgm_info.mon_code = vcpu->arch.sie_block->tecmc;
break;
case PGM_VECTOR_PROCESSING:
case PGM_DATA:
- pgm_info->data_exc_code = vcpu->arch.sie_block->dxc;
+ pgm_info.data_exc_code = vcpu->arch.sie_block->dxc;
break;
case PGM_PROTECTION:
- pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
- pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+ pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
break;
default:
break;
}
if (vcpu->arch.sie_block->iprcc & PGM_PER) {
- pgm_info->per_code = vcpu->arch.sie_block->perc;
- pgm_info->per_atmid = vcpu->arch.sie_block->peratmid;
- pgm_info->per_address = vcpu->arch.sie_block->peraddr;
- pgm_info->per_access_id = vcpu->arch.sie_block->peraid;
+ pgm_info.per_code = vcpu->arch.sie_block->perc;
+ pgm_info.per_atmid = vcpu->arch.sie_block->peratmid;
+ pgm_info.per_address = vcpu->arch.sie_block->peraddr;
+ pgm_info.per_access_id = vcpu->arch.sie_block->peraid;
}
+ return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}
/*
@@ -211,7 +226,6 @@ static int handle_itdb(struct kvm_vcpu *vcpu)
static int handle_prog(struct kvm_vcpu *vcpu)
{
- struct kvm_s390_pgm_info pgm_info;
psw_t psw;
int rc;
@@ -237,8 +251,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
if (rc)
return rc;
- __extract_prog_irq(vcpu, &pgm_info);
- return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+ return inject_prog_on_prog_intercept(vcpu);
}
/**
@@ -305,7 +318,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
/* Make sure that the source is paged-in */
rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
- reg2, &srcaddr, 0);
+ reg2, &srcaddr, GACC_FETCH);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
@@ -314,14 +327,14 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
/* Make sure that the destination is paged-in */
rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
- reg1, &dstaddr, 1);
+ reg1, &dstaddr, GACC_STORE);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
if (rc != 0)
return rc;
- kvm_s390_rewind_psw(vcpu, 4);
+ kvm_s390_retry_instr(vcpu);
return 0;
}
@@ -338,8 +351,10 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
{
+ if (kvm_is_ucontrol(vcpu->kvm))
+ return -EOPNOTSUPP;
+
switch (vcpu->arch.sie_block->icptcode) {
- case 0x00:
case 0x10:
case 0x18:
return handle_noop(vcpu);
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 373e32346d68..84efc2ba6a90 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -23,6 +23,7 @@
#include <asm/uaccess.h>
#include <asm/sclp.h>
#include <asm/isc.h>
+#include <asm/gmap.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "trace-s390.h"
@@ -34,6 +35,106 @@
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
+/* handle external calls via sigp interpretation facility */
+static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
+{
+ int c, scn;
+
+ if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+ return 0;
+
+ 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;
+
+ return c;
+}
+
+static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
+{
+ int expect, rc;
+
+ 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;
+
+ expect = old_val.value;
+ rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+
+ if (rc != expect) {
+ /* another external call is pending */
+ return -EBUSY;
+ }
+ atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+ 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;
+
+ 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;
+
+ expect = old.value;
+ rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+ WARN_ON(rc != expect); /* cannot clear? */
+}
+
int psw_extint_disabled(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
@@ -82,8 +183,9 @@ static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
{
- return (vcpu->arch.sie_block->cputm >> 63) &&
- cpu_timer_interrupts_enabled(vcpu);
+ if (!cpu_timer_interrupts_enabled(vcpu))
+ return 0;
+ return kvm_s390_get_cpu_timer(vcpu) >> 63;
}
static inline int is_ioirq(unsigned long irq_type)
@@ -235,23 +337,6 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu)
set_intercept_indicators_stop(vcpu);
}
-static u16 get_ilc(struct kvm_vcpu *vcpu)
-{
- switch (vcpu->arch.sie_block->icptcode) {
- case ICPT_INST:
- case ICPT_INSTPROGI:
- case ICPT_OPEREXC:
- case ICPT_PARTEXEC:
- case ICPT_IOINST:
- /* last instruction only stored for these icptcodes */
- return insn_length(vcpu->arch.sie_block->ipa >> 8);
- case ICPT_PROGI:
- return vcpu->arch.sie_block->pgmilc;
- default:
- return 0;
- }
-}
-
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -399,9 +484,9 @@ static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
rc = write_guest_lc(vcpu,
- offsetof(struct _lowcore, restart_old_psw),
+ offsetof(struct lowcore, restart_old_psw),
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
+ 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;
@@ -488,7 +573,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_pgm_info pgm_info;
int rc = 0, nullifying = false;
- u16 ilc = get_ilc(vcpu);
+ u16 ilen;
spin_lock(&li->lock);
pgm_info = li->irq.pgm;
@@ -496,8 +581,9 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
memset(&li->irq.pgm, 0, sizeof(pgm_info));
spin_unlock(&li->lock);
- VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
- pgm_info.code, ilc);
+ 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++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info.code, 0);
@@ -581,10 +667,11 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
(u8 *) __LC_PER_ACCESS_ID);
}
- if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
- kvm_s390_rewind_psw(vcpu, ilc);
+ if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND))
+ kvm_s390_rewind_psw(vcpu, ilen);
- rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
+ /* 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,
@@ -792,13 +879,11 @@ static const deliver_irq_t deliver_irq_funcs[] = {
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
if (!sclp.has_sigpif)
return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
- return (sigp_ctrl & SIGP_CTRL_C) &&
- (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
+ return sca_ext_call_pending(vcpu, NULL);
}
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
@@ -825,9 +910,35 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
}
+static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
+{
+ u64 now, 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)
+ 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));
+ }
+ } else if (cpu_timer_interrupts_enabled(vcpu)) {
+ sltime = kvm_s390_get_cpu_timer(vcpu);
+ /* already expired? */
+ if (sltime >> 63)
+ return 0;
+ }
+ return sltime;
+}
+
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
- u64 now, sltime;
+ u64 sltime;
vcpu->stat.exit_wait_state++;
@@ -840,22 +951,20 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP; /* disabled wait */
}
- if (!ckc_interrupts_enabled(vcpu)) {
+ if (!ckc_interrupts_enabled(vcpu) &&
+ !cpu_timer_interrupts_enabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
__set_cpu_idle(vcpu);
goto no_timer;
}
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-
- /* underflow */
- if (vcpu->arch.sie_block->ckc < now)
+ sltime = __calculate_sltime(vcpu);
+ if (!sltime)
return 0;
__set_cpu_idle(vcpu);
hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
- VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
+ VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
no_timer:
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
kvm_vcpu_block(vcpu);
@@ -868,13 +977,13 @@ no_timer:
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
- if (waitqueue_active(&vcpu->wq)) {
+ if (swait_active(&vcpu->wq)) {
/*
* The vcpu gave up the cpu voluntarily, mark it as a good
* yield-candidate.
*/
vcpu->preempted = true;
- wake_up_interruptible(&vcpu->wq);
+ swake_up(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
@@ -882,18 +991,16 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
struct kvm_vcpu *vcpu;
- u64 now, sltime;
+ u64 sltime;
vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+ sltime = __calculate_sltime(vcpu);
/*
* If the monotonic clock runs faster than the tod clock we might be
* woken up too early and have to go back to sleep to avoid deadlocks.
*/
- if (vcpu->arch.sie_block->ckc > now &&
- hrtimer_forward_now(timer, ns_to_ktime(sltime)))
+ if (sltime && hrtimer_forward_now(timer, ns_to_ktime(sltime)))
return HRTIMER_RESTART;
kvm_s390_vcpu_wakeup(vcpu);
return HRTIMER_NORESTART;
@@ -909,9 +1016,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
memset(&li->irq, 0, sizeof(li->irq));
spin_unlock(&li->lock);
- /* clear pending external calls set by sigp interpretation facility */
- atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
- vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
+ sca_clear_ext_call(vcpu);
}
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
@@ -963,8 +1068,16 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
irq->u.pgm.code, 0);
+ if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) {
+ /* auto detection if no valid ILC was given */
+ irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK;
+ irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu);
+ irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID;
+ }
+
if (irq->u.pgm.code == PGM_PER) {
li->irq.pgm.code |= PGM_PER;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify PER related information */
li->irq.pgm.per_address = irq->u.pgm.per_address;
li->irq.pgm.per_code = irq->u.pgm.per_code;
@@ -973,6 +1086,7 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
} else if (!(irq->u.pgm.code & PGM_PER)) {
li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) |
irq->u.pgm.code;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify non-PER information */
li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code;
li->irq.pgm.mon_code = irq->u.pgm.mon_code;
@@ -1003,21 +1117,6 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
return 0;
}
-static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
-{
- unsigned char new_val, old_val;
- uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
- new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
- old_val = *sigp_ctrl & ~SIGP_CTRL_C;
- if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
- /* another external call is pending */
- return -EBUSY;
- }
- atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
- return 0;
-}
-
static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -1030,12 +1129,11 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
src_id, 0);
/* sending vcpu invalid */
- if (src_id >= KVM_MAX_VCPUS ||
- kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
+ if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
return -EINVAL;
if (sclp.has_sigpif)
- return __inject_extcall_sigpif(vcpu, src_id);
+ return sca_inject_ext_call(vcpu, src_id);
if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
return -EBUSY;
@@ -1110,6 +1208,10 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
irq->u.emerg.code, 0);
+ /* sending vcpu invalid */
+ if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL)
+ return -EINVAL;
+
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);
@@ -2200,7 +2302,7 @@ 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)
{
- uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+ int scn;
unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
unsigned long pending_irqs;
@@ -2240,14 +2342,12 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
}
}
- if ((sigp_ctrl & SIGP_CTRL_C) &&
- (atomic_read(&vcpu->arch.sie_block->cpuflags) &
- CPUSTAT_ECALL_PEND)) {
+ if (sca_ext_call_pending(vcpu, &scn)) {
if (n + sizeof(irq) > len)
return -ENOBUFS;
memset(&irq, 0, sizeof(irq));
irq.type = KVM_S390_INT_EXTERNAL_CALL;
- irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+ irq.u.extcall.code = scn;
if (copy_to_user(&buf[n], &irq, sizeof(irq)))
return -EFAULT;
n += sizeof(irq);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8fe2f1c722dc..668c087513e5 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -30,6 +30,7 @@
#include <asm/lowcore.h>
#include <asm/etr.h>
#include <asm/pgtable.h>
+#include <asm/gmap.h>
#include <asm/nmi.h>
#include <asm/switch_to.h>
#include <asm/isc.h>
@@ -158,6 +159,8 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
kvm->arch.epoch -= *delta;
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.sie_block->epoch -= *delta;
+ if (vcpu->arch.cputm_enabled)
+ vcpu->arch.cputm_start += *delta;
}
}
return NOTIFY_OK;
@@ -246,7 +249,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
- r = KVM_MAX_VCPUS;
+ r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
+ : KVM_S390_BSCA_CPU_SLOTS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_USER_MEM_SLOTS;
@@ -257,6 +261,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_VECTOR_REGISTERS:
r = MACHINE_HAS_VX;
break;
+ case KVM_CAP_S390_RI:
+ r = test_facility(64);
+ break;
default:
r = 0;
}
@@ -270,19 +277,22 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
unsigned long address;
struct gmap *gmap = kvm->arch.gmap;
- down_read(&gmap->mm->mmap_sem);
/* Loop over all guest pages */
last_gfn = memslot->base_gfn + memslot->npages;
for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
address = gfn_to_hva_memslot(memslot, cur_gfn);
- if (gmap_test_and_clear_dirty(address, gmap))
+ if (test_and_clear_guest_dirty(gmap->mm, address))
mark_page_dirty(kvm, cur_gfn);
+ if (fatal_signal_pending(current))
+ return;
+ cond_resched();
}
- up_read(&gmap->mm->mmap_sem);
}
/* Section: vm related */
+static void sca_del_vcpu(struct kvm_vcpu *vcpu);
+
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
@@ -342,15 +352,33 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
r = 0;
break;
case KVM_CAP_S390_VECTOR_REGISTERS:
- if (MACHINE_HAS_VX) {
- set_kvm_facility(kvm->arch.model.fac->mask, 129);
- set_kvm_facility(kvm->arch.model.fac->list, 129);
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus)) {
+ r = -EBUSY;
+ } else if (MACHINE_HAS_VX) {
+ set_kvm_facility(kvm->arch.model.fac_mask, 129);
+ set_kvm_facility(kvm->arch.model.fac_list, 129);
r = 0;
} else
r = -EINVAL;
+ mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
r ? "(not available)" : "(success)");
break;
+ case KVM_CAP_S390_RI:
+ r = -EINVAL;
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus)) {
+ r = -EBUSY;
+ } else if (test_facility(64)) {
+ set_kvm_facility(kvm->arch.model.fac_mask, 64);
+ set_kvm_facility(kvm->arch.model.fac_list, 64);
+ r = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
+ r ? "(not available)" : "(success)");
+ break;
case KVM_CAP_S390_USER_STSI:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
kvm->arch.user_stsi = 1;
@@ -371,8 +399,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att
case KVM_S390_VM_MEM_LIMIT_SIZE:
ret = 0;
VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
- kvm->arch.gmap->asce_end);
- if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
+ kvm->arch.mem_limit);
+ if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
ret = -EFAULT;
break;
default:
@@ -424,9 +452,17 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
if (get_user(new_limit, (u64 __user *)attr->addr))
return -EFAULT;
- if (new_limit > kvm->arch.gmap->asce_end)
+ if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
+ new_limit > kvm->arch.mem_limit)
return -E2BIG;
+ if (!new_limit)
+ return -EINVAL;
+
+ /* gmap_alloc takes last usable address */
+ if (new_limit != KVM_S390_NO_MEM_LIMIT)
+ new_limit -= 1;
+
ret = -EBUSY;
mutex_lock(&kvm->lock);
if (atomic_read(&kvm->online_vcpus) == 0) {
@@ -443,7 +479,9 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
}
}
mutex_unlock(&kvm->lock);
- VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit);
+ VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
+ VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+ (void *) kvm->arch.gmap->asce);
break;
}
default:
@@ -617,7 +655,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
memcpy(&kvm->arch.model.cpu_id, &proc->cpuid,
sizeof(struct cpuid));
kvm->arch.model.ibc = proc->ibc;
- memcpy(kvm->arch.model.fac->list, proc->fac_list,
+ memcpy(kvm->arch.model.fac_list, proc->fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
} else
ret = -EFAULT;
@@ -651,7 +689,8 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
}
memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid));
proc->ibc = kvm->arch.model.ibc;
- memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE);
+ memcpy(&proc->fac_list, kvm->arch.model.fac_list,
+ S390_ARCH_FAC_LIST_SIZE_BYTE);
if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
ret = -EFAULT;
kfree(proc);
@@ -671,7 +710,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
}
get_cpu_id((struct cpuid *) &mach->cpuid);
mach->ibc = sclp.ibc;
- memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
+ memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
@@ -1020,7 +1059,7 @@ static int kvm_s390_apxa_installed(void)
u8 config[128];
int cc;
- if (test_facility(2) && test_facility(12)) {
+ if (test_facility(12)) {
cc = kvm_s390_query_ap_config(config);
if (cc)
@@ -1048,16 +1087,12 @@ static void kvm_s390_get_cpu_id(struct cpuid *cpu_id)
cpu_id->version = 0xff;
}
-static int kvm_s390_crypto_init(struct kvm *kvm)
+static void kvm_s390_crypto_init(struct kvm *kvm)
{
if (!test_kvm_facility(kvm, 76))
- return 0;
-
- kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb),
- GFP_KERNEL | GFP_DMA);
- if (!kvm->arch.crypto.crycb)
- return -ENOMEM;
+ return;
+ kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
kvm_s390_set_crycb_format(kvm);
/* Enable AES/DEA protected key functions by default */
@@ -1067,8 +1102,15 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
+}
- return 0;
+static void sca_dispose(struct kvm *kvm)
+{
+ if (kvm->arch.use_esca)
+ free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
+ else
+ free_page((unsigned long)(kvm->arch.sca));
+ kvm->arch.sca = NULL;
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
@@ -1094,14 +1136,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
rc = -ENOMEM;
- kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+ kvm->arch.use_esca = 0; /* start with basic SCA */
+ rwlock_init(&kvm->arch.sca_lock);
+ kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
if (!kvm->arch.sca)
goto out_err;
spin_lock(&kvm_lock);
sca_offset += 16;
- if (sca_offset + sizeof(struct sca_block) > PAGE_SIZE)
+ if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
sca_offset = 0;
- kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
+ kvm->arch.sca = (struct bsca_block *)
+ ((char *) kvm->arch.sca + sca_offset);
spin_unlock(&kvm_lock);
sprintf(debug_name, "kvm-%u", current->pid);
@@ -1110,37 +1155,30 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (!kvm->arch.dbf)
goto out_err;
- /*
- * The architectural maximum amount of facilities is 16 kbit. To store
- * this amount, 2 kbyte of memory is required. Thus we need a full
- * page to hold the guest facility list (arch.model.fac->list) and the
- * facility mask (arch.model.fac->mask). Its address size has to be
- * 31 bits and word aligned.
- */
- kvm->arch.model.fac =
- (struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
- if (!kvm->arch.model.fac)
+ kvm->arch.sie_page2 =
+ (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+ if (!kvm->arch.sie_page2)
goto out_err;
/* Populate the facility mask initially. */
- memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
+ memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
if (i < kvm_s390_fac_list_mask_size())
- kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i];
+ kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
else
- kvm->arch.model.fac->mask[i] = 0UL;
+ kvm->arch.model.fac_mask[i] = 0UL;
}
/* Populate the facility list initially. */
- memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask,
+ kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
+ memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
kvm->arch.model.ibc = sclp.ibc & 0x0fff;
- if (kvm_s390_crypto_init(kvm) < 0)
- goto out_err;
+ kvm_s390_crypto_init(kvm);
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
@@ -1153,8 +1191,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (type & KVM_VM_S390_UCONTROL) {
kvm->arch.gmap = NULL;
+ kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
} else {
- kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
+ if (sclp.hamax == U64_MAX)
+ kvm->arch.mem_limit = TASK_MAX_SIZE;
+ else
+ kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
+ sclp.hamax + 1);
+ kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
if (!kvm->arch.gmap)
goto out_err;
kvm->arch.gmap->private = kvm;
@@ -1166,14 +1210,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.epoch = 0;
spin_lock_init(&kvm->arch.start_stop_lock);
- KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
+ KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
return 0;
out_err:
- kfree(kvm->arch.crypto.crycb);
- free_page((unsigned long)kvm->arch.model.fac);
+ free_page((unsigned long)kvm->arch.sie_page2);
debug_unregister(kvm->arch.dbf);
- free_page((unsigned long)(kvm->arch.sca));
+ sca_dispose(kvm);
KVM_EVENT(3, "creation of vm failed: %d", rc);
return rc;
}
@@ -1184,14 +1227,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
kvm_s390_clear_local_irqs(vcpu);
kvm_clear_async_pf_completion_queue(vcpu);
- if (!kvm_is_ucontrol(vcpu->kvm)) {
- clear_bit(63 - vcpu->vcpu_id,
- (unsigned long *) &vcpu->kvm->arch.sca->mcn);
- if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
- (__u64) vcpu->arch.sie_block)
- vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
- }
- smp_mb();
+ if (!kvm_is_ucontrol(vcpu->kvm))
+ sca_del_vcpu(vcpu);
if (kvm_is_ucontrol(vcpu->kvm))
gmap_free(vcpu->arch.gmap);
@@ -1223,15 +1260,14 @@ static void kvm_free_vcpus(struct kvm *kvm)
void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_free_vcpus(kvm);
- free_page((unsigned long)kvm->arch.model.fac);
- free_page((unsigned long)(kvm->arch.sca));
+ sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
- kfree(kvm->arch.crypto.crycb);
+ free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
gmap_free(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
kvm_s390_clear_float_irqs(kvm);
- KVM_EVENT(3, "vm 0x%p destroyed", kvm);
+ KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
}
/* Section: vcpu related */
@@ -1245,6 +1281,117 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
return 0;
}
+static void sca_del_vcpu(struct kvm_vcpu *vcpu)
+{
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+
+ clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+ sca->cpu[vcpu->vcpu_id].sda = 0;
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+ clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+ sca->cpu[vcpu->vcpu_id].sda = 0;
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+static void sca_add_vcpu(struct kvm_vcpu *vcpu)
+{
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+
+ sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+ vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
+ vcpu->arch.sie_block->ecb2 |= 0x04U;
+ set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+ sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
+ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+ vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+ set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+/* Basic SCA to Extended SCA data copy routines */
+static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
+{
+ d->sda = s->sda;
+ d->sigp_ctrl.c = s->sigp_ctrl.c;
+ d->sigp_ctrl.scn = s->sigp_ctrl.scn;
+}
+
+static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
+{
+ int i;
+
+ d->ipte_control = s->ipte_control;
+ d->mcn[0] = s->mcn;
+ for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
+ sca_copy_entry(&d->cpu[i], &s->cpu[i]);
+}
+
+static int sca_switch_to_extended(struct kvm *kvm)
+{
+ struct bsca_block *old_sca = kvm->arch.sca;
+ struct esca_block *new_sca;
+ struct kvm_vcpu *vcpu;
+ unsigned int vcpu_idx;
+ u32 scaol, scaoh;
+
+ new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
+ if (!new_sca)
+ return -ENOMEM;
+
+ scaoh = (u32)((u64)(new_sca) >> 32);
+ scaol = (u32)(u64)(new_sca) & ~0x3fU;
+
+ kvm_s390_vcpu_block_all(kvm);
+ write_lock(&kvm->arch.sca_lock);
+
+ sca_copy_b_to_e(new_sca, old_sca);
+
+ kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
+ vcpu->arch.sie_block->scaoh = scaoh;
+ vcpu->arch.sie_block->scaol = scaol;
+ vcpu->arch.sie_block->ecb2 |= 0x04U;
+ }
+ kvm->arch.sca = new_sca;
+ kvm->arch.use_esca = 1;
+
+ write_unlock(&kvm->arch.sca_lock);
+ kvm_s390_vcpu_unblock_all(kvm);
+
+ free_page((unsigned long)old_sca);
+
+ VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+ old_sca, kvm->arch.sca);
+ return 0;
+}
+
+static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
+{
+ int rc;
+
+ if (id < KVM_S390_BSCA_CPU_SLOTS)
+ return true;
+ if (!sclp.has_esca)
+ return false;
+
+ mutex_lock(&kvm->lock);
+ rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
+ mutex_unlock(&kvm->lock);
+
+ return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
+}
+
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1255,8 +1402,15 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
KVM_SYNC_CRS |
KVM_SYNC_ARCH0 |
KVM_SYNC_PFAULT;
- if (test_kvm_facility(vcpu->kvm, 129))
+ if (test_kvm_facility(vcpu->kvm, 64))
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+ /* fprs can be synchronized via vrs, even if the guest has no vx. With
+ * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+ */
+ if (MACHINE_HAS_VX)
vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+ else
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
if (kvm_is_ucontrol(vcpu->kvm))
return __kvm_ucontrol_vcpu_init(vcpu);
@@ -1264,44 +1418,105 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
return 0;
}
-/*
- * Backs up the current FP/VX register save area on a particular
- * destination. Used to switch between different register save
- * areas.
- */
-static inline void save_fpu_to(struct fpu *dst)
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
- dst->fpc = current->thread.fpu.fpc;
- dst->regs = current->thread.fpu.regs;
+ WARN_ON_ONCE(vcpu->arch.cputm_start != 0);
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ vcpu->arch.cputm_start = get_tod_clock_fast();
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
}
-/*
- * Switches the FP/VX register save area from which to lazy
- * restore register contents.
- */
-static inline void load_fpu_from(struct fpu *from)
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __stop_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
- current->thread.fpu.fpc = from->fpc;
- current->thread.fpu.regs = from->regs;
+ WARN_ON_ONCE(vcpu->arch.cputm_start == 0);
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ vcpu->arch.sie_block->cputm -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+ vcpu->arch.cputm_start = 0;
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
}
-void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
- /* Save host register state */
- save_fpu_regs();
- save_fpu_to(&vcpu->arch.host_fpregs);
+ WARN_ON_ONCE(vcpu->arch.cputm_enabled);
+ vcpu->arch.cputm_enabled = true;
+ __start_cpu_timer_accounting(vcpu);
+}
- if (test_kvm_facility(vcpu->kvm, 129)) {
- current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ WARN_ON_ONCE(!vcpu->arch.cputm_enabled);
+ __stop_cpu_timer_accounting(vcpu);
+ vcpu->arch.cputm_enabled = false;
+}
+
+static void enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ __enable_cpu_timer_accounting(vcpu);
+ preempt_enable();
+}
+
+static void disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ __disable_cpu_timer_accounting(vcpu);
+ preempt_enable();
+}
+
+/* set the cpu timer - may only be called from the VCPU thread itself */
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm)
+{
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ if (vcpu->arch.cputm_enabled)
+ vcpu->arch.cputm_start = get_tod_clock_fast();
+ vcpu->arch.sie_block->cputm = cputm;
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+ preempt_enable();
+}
+
+/* update and get the cpu timer - can also be called from other VCPU threads */
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
+{
+ unsigned int seq;
+ __u64 value;
+
+ if (unlikely(!vcpu->arch.cputm_enabled))
+ return vcpu->arch.sie_block->cputm;
+
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ do {
+ seq = raw_read_seqcount(&vcpu->arch.cputm_seqcount);
/*
- * Use the register save area in the SIE-control block
- * for register restore and save in kvm_arch_vcpu_put()
+ * If the writer would ever execute a read in the critical
+ * section, e.g. in irq context, we have a deadlock.
*/
- current->thread.fpu.vxrs =
- (__vector128 *)&vcpu->run->s.regs.vrs;
- } else
- load_fpu_from(&vcpu->arch.guest_fpregs);
+ WARN_ON_ONCE((seq & 1) && smp_processor_id() == vcpu->cpu);
+ value = vcpu->arch.sie_block->cputm;
+ /* if cputm_start is 0, accounting is being started/stopped */
+ if (likely(vcpu->arch.cputm_start))
+ value -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+ } while (read_seqcount_retry(&vcpu->arch.cputm_seqcount, seq & ~1));
+ preempt_enable();
+ return value;
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+ /* Save host register state */
+ save_fpu_regs();
+ vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
+ vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
+ if (MACHINE_HAS_VX)
+ current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+ else
+ current->thread.fpu.regs = vcpu->run->s.regs.fprs;
+ current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
if (test_fp_ctl(current->thread.fpu.fpc))
/* User space provided an invalid FPC, let's clear it */
current->thread.fpu.fpc = 0;
@@ -1310,26 +1525,26 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
restore_access_regs(vcpu->run->s.regs.acrs);
gmap_enable(vcpu->arch.gmap);
atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+ __start_cpu_timer_accounting(vcpu);
+ vcpu->cpu = cpu;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ vcpu->cpu = -1;
+ if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+ __stop_cpu_timer_accounting(vcpu);
atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
gmap_disable(vcpu->arch.gmap);
+ /* Save guest register state */
save_fpu_regs();
+ vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
- if (test_kvm_facility(vcpu->kvm, 129))
- /*
- * kvm_arch_vcpu_load() set up the register save area to
- * the &vcpu->run->s.regs.vrs and, thus, the vector registers
- * are already saved. Only the floating-point control must be
- * copied.
- */
- vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
- else
- save_fpu_to(&vcpu->arch.guest_fpregs);
- load_fpu_from(&vcpu->arch.host_fpregs);
+ /* Restore host register state */
+ current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
+ current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
save_access_regs(vcpu->run->s.regs.acrs);
restore_access_regs(vcpu->arch.host_acrs);
@@ -1341,14 +1556,15 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->gpsw.mask = 0UL;
vcpu->arch.sie_block->gpsw.addr = 0UL;
kvm_s390_set_prefix(vcpu, 0);
- vcpu->arch.sie_block->cputm = 0UL;
+ kvm_s390_set_cpu_timer(vcpu, 0);
vcpu->arch.sie_block->ckc = 0UL;
vcpu->arch.sie_block->todpr = 0;
memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
vcpu->arch.sie_block->gcr[0] = 0xE0UL;
vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
- vcpu->arch.guest_fpregs.fpc = 0;
- asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+ /* make sure the new fpc will be lazily loaded */
+ save_fpu_regs();
+ current->thread.fpu.fpc = 0;
vcpu->arch.sie_block->gbea = 1;
vcpu->arch.sie_block->pp = 0;
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1365,8 +1581,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
preempt_enable();
mutex_unlock(&vcpu->kvm->lock);
- if (!kvm_is_ucontrol(vcpu->kvm))
+ if (!kvm_is_ucontrol(vcpu->kvm)) {
vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+ sca_add_vcpu(vcpu);
+ }
+
}
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
@@ -1407,7 +1626,8 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
vcpu->arch.cpu_id = model->cpu_id;
vcpu->arch.sie_block->ibc = model->ibc;
- vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
+ if (test_kvm_facility(vcpu->kvm, 7))
+ vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
}
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -1435,10 +1655,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->eca |= 1;
if (sclp.has_sigpif)
vcpu->arch.sie_block->eca |= 0x10000000U;
+ if (test_kvm_facility(vcpu->kvm, 64))
+ vcpu->arch.sie_block->ecb3 |= 0x01;
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
vcpu->arch.sie_block->ecd |= 0x20000000;
}
+ vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
if (vcpu->kvm->arch.use_cmma) {
@@ -1461,7 +1684,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
struct sie_page *sie_page;
int rc = -EINVAL;
- if (id >= KVM_MAX_VCPUS)
+ if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
goto out;
rc = -ENOMEM;
@@ -1478,42 +1701,16 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
vcpu->arch.sie_block->icpua = id;
- if (!kvm_is_ucontrol(kvm)) {
- if (!kvm->arch.sca) {
- WARN_ON_ONCE(1);
- goto out_free_cpu;
- }
- if (!kvm->arch.sca->cpu[id].sda)
- kvm->arch.sca->cpu[id].sda =
- (__u64) vcpu->arch.sie_block;
- vcpu->arch.sie_block->scaoh =
- (__u32)(((__u64)kvm->arch.sca) >> 32);
- vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
- set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
- }
-
spin_lock_init(&vcpu->arch.local_int.lock);
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
vcpu->arch.local_int.wq = &vcpu->wq;
vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
-
- /*
- * Allocate a save area for floating-point registers. If the vector
- * extension is available, register contents are saved in the SIE
- * control block. The allocated save area is still required in
- * particular places, for example, in kvm_s390_vcpu_store_status().
- */
- vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
- GFP_KERNEL);
- if (!vcpu->arch.guest_fpregs.fprs) {
- rc = -ENOMEM;
- goto out_free_sie_block;
- }
+ seqcount_init(&vcpu->arch.cputm_seqcount);
rc = kvm_vcpu_init(vcpu, kvm, id);
if (rc)
goto out_free_sie_block;
- VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+ VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
vcpu->arch.sie_block);
trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
@@ -1608,7 +1805,7 @@ static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CPU_TIMER:
- r = put_user(vcpu->arch.sie_block->cputm,
+ r = put_user(kvm_s390_get_cpu_timer(vcpu),
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CLOCK_COMP:
@@ -1646,6 +1843,7 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
struct kvm_one_reg *reg)
{
int r = -EINVAL;
+ __u64 val;
switch (reg->id) {
case KVM_REG_S390_TODPR:
@@ -1657,8 +1855,9 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CPU_TIMER:
- r = get_user(vcpu->arch.sie_block->cputm,
- (u64 __user *)reg->addr);
+ r = get_user(val, (u64 __user *)reg->addr);
+ if (!r)
+ kvm_s390_set_cpu_timer(vcpu, val);
break;
case KVM_REG_S390_CLOCK_COMP:
r = get_user(vcpu->arch.sie_block->ckc,
@@ -1730,19 +1929,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
+ /* make sure the new values will be lazily loaded */
+ save_fpu_regs();
if (test_fp_ctl(fpu->fpc))
return -EINVAL;
- memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
- vcpu->arch.guest_fpregs.fpc = fpu->fpc;
- save_fpu_regs();
- load_fpu_from(&vcpu->arch.guest_fpregs);
+ current->thread.fpu.fpc = fpu->fpc;
+ if (MACHINE_HAS_VX)
+ convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+ else
+ memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
return 0;
}
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
- fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+ /* make sure we have the latest values */
+ save_fpu_regs();
+ if (MACHINE_HAS_VX)
+ convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+ else
+ memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+ fpu->fpc = current->thread.fpu.fpc;
return 0;
}
@@ -2009,7 +2216,8 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
*/
kvm_check_async_pf_completion(vcpu);
- memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
+ vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
+ vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
if (need_resched())
schedule();
@@ -2042,8 +2250,10 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
{
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
- u8 opcode;
+ struct kvm_s390_pgm_info pgm_info = {
+ .code = PGM_ADDRESSING,
+ };
+ u8 opcode, ilen;
int rc;
VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
@@ -2057,18 +2267,25 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
* to look up the current opcode to get the length of the instruction
* to be able to forward the PSW.
*/
- rc = read_guest(vcpu, psw->addr, 0, &opcode, 1);
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- psw->addr = __rewind_psw(*psw, -insn_length(opcode));
-
- return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ rc = read_guest_instr(vcpu, &opcode, 1);
+ ilen = insn_length(opcode);
+ if (rc < 0) {
+ return rc;
+ } else if (rc) {
+ /* Instruction-Fetching Exceptions - we can't detect the ilen.
+ * Forward by arbitrary ilc, injection will take care of
+ * nullification if necessary.
+ */
+ pgm_info = vcpu->arch.pgm;
+ ilen = 4;
+ }
+ pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID;
+ kvm_s390_forward_psw(vcpu, ilen);
+ return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
- int rc = -1;
-
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
@@ -2076,40 +2293,36 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
if (guestdbg_enabled(vcpu))
kvm_s390_restore_guest_per_regs(vcpu);
- if (exit_reason >= 0) {
- rc = 0;
+ vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
+ vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
+
+ if (vcpu->arch.sie_block->icptcode > 0) {
+ int rc = kvm_handle_sie_intercept(vcpu);
+
+ if (rc != -EOPNOTSUPP)
+ return rc;
+ vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
+ vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+ vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
+ vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
+ return -EREMOTE;
+ } else if (exit_reason != -EFAULT) {
+ vcpu->stat.exit_null++;
+ return 0;
} else if (kvm_is_ucontrol(vcpu->kvm)) {
vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
vcpu->run->s390_ucontrol.trans_exc_code =
current->thread.gmap_addr;
vcpu->run->s390_ucontrol.pgm_code = 0x10;
- rc = -EREMOTE;
-
+ return -EREMOTE;
} else if (current->thread.gmap_pfault) {
trace_kvm_s390_major_guest_pfault(vcpu);
current->thread.gmap_pfault = 0;
- if (kvm_arch_setup_async_pf(vcpu)) {
- rc = 0;
- } else {
- gpa_t gpa = current->thread.gmap_addr;
- rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
- }
+ if (kvm_arch_setup_async_pf(vcpu))
+ return 0;
+ return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
}
-
- if (rc == -1)
- rc = vcpu_post_run_fault_in_sie(vcpu);
-
- memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
-
- if (rc == 0) {
- if (kvm_is_ucontrol(vcpu->kvm))
- /* Don't exit for host interrupts. */
- rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
- else
- rc = kvm_handle_sie_intercept(vcpu);
- }
-
- return rc;
+ return vcpu_post_run_fault_in_sie(vcpu);
}
static int __vcpu_run(struct kvm_vcpu *vcpu)
@@ -2134,10 +2347,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
*/
local_irq_disable();
__kvm_guest_enter();
+ __disable_cpu_timer_accounting(vcpu);
local_irq_enable();
exit_reason = sie64a(vcpu->arch.sie_block,
vcpu->run->s.regs.gprs);
local_irq_disable();
+ __enable_cpu_timer_accounting(vcpu);
__kvm_guest_exit();
local_irq_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
@@ -2161,7 +2376,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
- vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm;
+ kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
@@ -2183,7 +2398,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
- kvm_run->s.regs.cputm = vcpu->arch.sie_block->cputm;
+ kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
@@ -2215,6 +2430,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
sync_regs(vcpu, kvm_run);
+ enable_cpu_timer_accounting(vcpu);
might_fault();
rc = __vcpu_run(vcpu);
@@ -2229,21 +2445,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
rc = 0;
}
- if (rc == -EOPNOTSUPP) {
- /* intercept cannot be handled in-kernel, prepare kvm-run */
- kvm_run->exit_reason = KVM_EXIT_S390_SIEIC;
- kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
- kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
- kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
- rc = 0;
- }
-
if (rc == -EREMOTE) {
- /* intercept was handled, but userspace support is needed
- * kvm_run has been prepared by the handler */
+ /* userspace support is needed, kvm_run has been prepared */
rc = 0;
}
+ disable_cpu_timer_accounting(vcpu);
store_regs(vcpu, kvm_run);
if (vcpu->sigset_active)
@@ -2262,41 +2469,51 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
{
unsigned char archmode = 1;
+ freg_t fprs[NUM_FPRS];
unsigned int px;
- u64 clkcomp;
+ u64 clkcomp, cputm;
int rc;
+ px = kvm_s390_get_prefix(vcpu);
if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
if (write_guest_abs(vcpu, 163, &archmode, 1))
return -EFAULT;
- gpa = SAVE_AREA_BASE;
+ gpa = 0;
} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
if (write_guest_real(vcpu, 163, &archmode, 1))
return -EFAULT;
- gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE);
+ gpa = px;
+ } else
+ gpa -= __LC_FPREGS_SAVE_AREA;
+
+ /* manually convert vector registers if necessary */
+ if (MACHINE_HAS_VX) {
+ convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
+ rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+ fprs, 128);
+ } else {
+ rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+ vcpu->run->s.regs.fprs, 128);
}
- rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs),
- vcpu->arch.guest_fpregs.fprs, 128);
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs),
+ rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
vcpu->run->s.regs.gprs, 128);
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw),
+ rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
&vcpu->arch.sie_block->gpsw, 16);
- px = kvm_s390_get_prefix(vcpu);
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
+ rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
&px, 4);
- rc |= write_guest_abs(vcpu,
- gpa + offsetof(struct save_area, fp_ctrl_reg),
- &vcpu->arch.guest_fpregs.fpc, 4);
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg),
+ rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
+ &vcpu->run->s.regs.fpc, 4);
+ rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
&vcpu->arch.sie_block->todpr, 4);
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer),
- &vcpu->arch.sie_block->cputm, 8);
+ cputm = kvm_s390_get_cpu_timer(vcpu);
+ rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
+ &cputm, 8);
clkcomp = vcpu->arch.sie_block->ckc >> 8;
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp),
+ rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
&clkcomp, 8);
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs),
+ rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA,
&vcpu->run->s.regs.acrs, 64);
- rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs),
+ rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA,
&vcpu->arch.sie_block->gcr, 128);
return rc ? -EFAULT : 0;
}
@@ -2309,19 +2526,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
* it into the save area
*/
save_fpu_regs();
- if (test_kvm_facility(vcpu->kvm, 129)) {
- /*
- * If the vector extension is available, the vector registers
- * which overlaps with floating-point registers are saved in
- * the SIE-control block. Hence, extract the floating-point
- * registers and the FPC value and store them in the
- * guest_fpregs structure.
- */
- vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc;
- convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs,
- current->thread.fpu.vxrs);
- } else
- save_fpu_to(&vcpu->arch.guest_fpregs);
+ vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
save_access_regs(vcpu->run->s.regs.acrs);
return kvm_s390_store_status_unloaded(vcpu, addr);
@@ -2508,7 +2713,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
switch (mop->op) {
case KVM_S390_MEMOP_LOGICAL_READ:
if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+ mop->size, GACC_FETCH);
break;
}
r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
@@ -2519,7 +2725,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
break;
case KVM_S390_MEMOP_LOGICAL_WRITE:
if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+ mop->size, GACC_STORE);
break;
}
if (copy_from_user(tmpbuf, uaddr, mop->size)) {
@@ -2732,6 +2939,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
if (mem->memory_size & 0xffffful)
return -EINVAL;
+ if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+ return -EINVAL;
+
return 0;
}
@@ -2763,6 +2973,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
static int __init kvm_s390_init(void)
{
+ if (!sclp.has_sief2) {
+ pr_info("SIE not available\n");
+ return -ENODEV;
+ }
+
return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 1e70e00d3c5e..8621ab00ec8e 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -19,6 +19,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/facility.h>
+#include <asm/processor.h>
typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
@@ -53,6 +54,11 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
}
+static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
+{
+ return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_WAIT;
+}
+
static inline int kvm_is_ucontrol(struct kvm *kvm)
{
#ifdef CONFIG_KVM_S390_UCONTROL
@@ -154,8 +160,8 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
/* test availability of facility in a kvm instance */
static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr)
{
- return __test_facility(nr, kvm->arch.model.fac->mask) &&
- __test_facility(nr, kvm->arch.model.fac->list);
+ return __test_facility(nr, kvm->arch.model.fac_mask) &&
+ __test_facility(nr, kvm->arch.model.fac_list);
}
static inline int set_kvm_facility(u64 *fac_list, unsigned long nr)
@@ -212,8 +218,22 @@ int kvm_s390_reinject_io_int(struct kvm *kvm,
int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
/* implemented in intercept.c */
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc);
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu);
int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+static inline void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+ struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+
+ sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilen);
+}
+static inline void kvm_s390_forward_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+ kvm_s390_rewind_psw(vcpu, -ilen);
+}
+static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu)
+{
+ kvm_s390_rewind_psw(vcpu, kvm_s390_get_ilen(vcpu));
+}
/* implemented in priv.c */
int is_valid_psw(psw_t *psw);
@@ -248,6 +268,8 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
unsigned long kvm_s390_fac_list_mask_size(void);
extern unsigned long kvm_s390_fac_list_mask[];
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
/* implemented in diag.c */
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
@@ -340,4 +362,11 @@ void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
+/* support for Basic/Extended SCA handling */
+static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
+{
+ struct bsca_block *sca = kvm->arch.sca; /* SCA version doesn't matter */
+
+ return &sca->ipte_control;
+}
#endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 77191b85ea7a..0a1591d3d25d 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -23,6 +23,7 @@
#include <asm/sysinfo.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
+#include <asm/gmap.h>
#include <asm/io.h>
#include <asm/ptrace.h>
#include <asm/compat.h>
@@ -173,7 +174,7 @@ static int handle_skey(struct kvm_vcpu *vcpu)
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- kvm_s390_rewind_psw(vcpu, 4);
+ kvm_s390_retry_instr(vcpu);
VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
return 0;
}
@@ -184,7 +185,7 @@ static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
if (psw_bits(vcpu->arch.sie_block->gpsw).p)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
- kvm_s390_rewind_psw(vcpu, 4);
+ kvm_s390_retry_instr(vcpu);
VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
return 0;
}
@@ -354,8 +355,8 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
* We need to shift the lower 32 facility bits (bit 0-31) from a u64
* into a u32 memory representation. They will remain bits 0-31.
*/
- fac = *vcpu->kvm->arch.model.fac->list >> 32;
- rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list),
+ fac = *vcpu->kvm->arch.model.fac_list >> 32;
+ rc = write_guest_lc(vcpu, offsetof(struct lowcore, stfl_fac_list),
&fac, sizeof(fac));
if (rc)
return rc;
@@ -660,7 +661,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
- if (!MACHINE_HAS_PFMF)
+ if (!test_kvm_facility(vcpu->kvm, 8))
return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
@@ -759,8 +760,8 @@ static int handle_essa(struct kvm_vcpu *vcpu)
if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- /* Rewind PSW to repeat the ESSA instruction */
- kvm_s390_rewind_psw(vcpu, 4);
+ /* Retry the ESSA instruction */
+ kvm_s390_retry_instr(vcpu);
vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */
cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
down_read(&gmap->mm->mmap_sem);
@@ -981,11 +982,12 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
ipte_lock(vcpu);
- ret = guest_translate_address(vcpu, address1, ar, &gpa, 1);
+ ret = guest_translate_address(vcpu, address1, ar, &gpa, GACC_STORE);
if (ret == PGM_PROTECTION) {
/* Write protected? Try again with read-only... */
cc = 1;
- ret = guest_translate_address(vcpu, address1, ar, &gpa, 0);
+ ret = guest_translate_address(vcpu, address1, ar, &gpa,
+ GACC_FETCH);
}
if (ret) {
if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) {
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index da690b69f9fe..77c22d685c7a 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -291,12 +291,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
u16 cpu_addr, u32 parameter, u64 *status_reg)
{
int rc;
- struct kvm_vcpu *dst_vcpu;
+ struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
- if (cpu_addr >= KVM_MAX_VCPUS)
- return SIGP_CC_NOT_OPERATIONAL;
-
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
if (!dst_vcpu)
return SIGP_CC_NOT_OPERATIONAL;
@@ -478,7 +474,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
if (order_code == SIGP_EXTERNAL_CALL) {
- dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
BUG_ON(dest_vcpu == NULL);
kvm_s390_vcpu_wakeup(dest_vcpu);
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index cc1d6c68356f..396485bca191 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -55,8 +55,8 @@ TRACE_EVENT(kvm_s390_create_vcpu,
__entry->sie_block = sie_block;
),
- TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
- __entry->vcpu, __entry->sie_block)
+ TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+ __entry->id, __entry->vcpu, __entry->sie_block)
);
TRACE_EVENT(kvm_s390_destroy_vcpu,
@@ -254,7 +254,7 @@ TRACE_EVENT(kvm_s390_enable_css,
__entry->kvm = kvm;
),
- TP_printk("enabling channel I/O support (kvm @ %p)\n",
+ TP_printk("enabling channel I/O support (kvm @ %pK)\n",
__entry->kvm)
);
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-20 11:42:25 +0000