summaryrefslogtreecommitdiff
path: root/arch/s390/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/kvm')
-rw-r--r--arch/s390/kvm/Kconfig2
-rw-r--r--arch/s390/kvm/diag.c37
-rw-r--r--arch/s390/kvm/gaccess.c337
-rw-r--r--arch/s390/kvm/gaccess.h21
-rw-r--r--arch/s390/kvm/guestdbg.c8
-rw-r--r--arch/s390/kvm/intercept.c84
-rw-r--r--arch/s390/kvm/interrupt.c2100
-rw-r--r--arch/s390/kvm/kvm-s390.c1215
-rw-r--r--arch/s390/kvm/kvm-s390.h98
-rw-r--r--arch/s390/kvm/priv.c270
-rw-r--r--arch/s390/kvm/sigp.c444
-rw-r--r--arch/s390/kvm/trace-s390.h21
12 files changed, 3245 insertions, 1392 deletions
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 10d529ac9821..5fce52cf0e57 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -26,7 +26,9 @@ config KVM
select KVM_ASYNC_PF
select KVM_ASYNC_PF_SYNC
select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
+ select SRCU
---help---
Support hosting paravirtualized guest machines using the SIE
virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 0161675878a2..fc7ec95848c3 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -28,22 +28,32 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
- if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end
+ if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end
|| start < 2 * PAGE_SIZE)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end);
vcpu->stat.diagnose_10++;
- /* we checked for start > end above */
- if (end < prefix || start >= prefix + 2 * PAGE_SIZE) {
- gmap_discard(start, end, vcpu->arch.gmap);
+ /*
+ * We checked for start >= end above, so lets check for the
+ * fast path (no prefix swap page involved)
+ */
+ if (end <= prefix || start >= prefix + 2 * PAGE_SIZE) {
+ gmap_discard(vcpu->arch.gmap, start, end);
} else {
- if (start < prefix)
- gmap_discard(start, prefix, vcpu->arch.gmap);
- if (end >= prefix)
- gmap_discard(prefix + 2 * PAGE_SIZE,
- end, vcpu->arch.gmap);
+ /*
+ * This is slow path. gmap_discard will check for start
+ * so lets split this into before prefix, prefix, after
+ * prefix and let gmap_discard make some of these calls
+ * NOPs.
+ */
+ gmap_discard(vcpu->arch.gmap, start, prefix);
+ if (start <= prefix)
+ gmap_discard(vcpu->arch.gmap, 0, 4096);
+ if (end > prefix + 4096)
+ gmap_discard(vcpu->arch.gmap, 4096, 8192);
+ gmap_discard(vcpu->arch.gmap, prefix + 2 * PAGE_SIZE, end);
}
return 0;
}
@@ -67,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
if (vcpu->run->s.regs.gprs[rx] & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm));
+ rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258)
@@ -176,7 +186,8 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
}
- kvm_s390_vcpu_stop(vcpu);
+ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+ kvm_s390_vcpu_stop(vcpu);
vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
@@ -202,7 +213,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
* - gpr 3 contains the virtqueue index (passed as datamatch)
* - gpr 4 contains the index on the bus (optionally)
*/
- ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS,
+ ret = kvm_io_bus_write_cookie(vcpu, KVM_VIRTIO_CCW_NOTIFY_BUS,
vcpu->run->s.regs.gprs[2] & 0xffffffff,
8, &vcpu->run->s.regs.gprs[3],
vcpu->run->s.regs.gprs[4]);
@@ -219,7 +230,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
{
- int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff;
+ int code = kvm_s390_get_base_disp_rs(vcpu, NULL) & 0xffff;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 4653ac6e182b..a7559f7207df 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -10,6 +10,7 @@
#include <asm/pgtable.h>
#include "kvm-s390.h"
#include "gaccess.h"
+#include <asm/switch_to.h>
union asce {
unsigned long val;
@@ -207,8 +208,54 @@ union raddress {
unsigned long pfra : 52; /* Page-Frame Real Address */
};
-static int ipte_lock_count;
-static DEFINE_MUTEX(ipte_mutex);
+union alet {
+ u32 val;
+ struct {
+ u32 reserved : 7;
+ u32 p : 1;
+ u32 alesn : 8;
+ u32 alen : 16;
+ };
+};
+
+union ald {
+ u32 val;
+ struct {
+ u32 : 1;
+ u32 alo : 24;
+ u32 all : 7;
+ };
+};
+
+struct ale {
+ unsigned long i : 1; /* ALEN-Invalid Bit */
+ unsigned long : 5;
+ unsigned long fo : 1; /* Fetch-Only Bit */
+ unsigned long p : 1; /* Private Bit */
+ unsigned long alesn : 8; /* Access-List-Entry Sequence Number */
+ unsigned long aleax : 16; /* Access-List-Entry Authorization Index */
+ unsigned long : 32;
+ unsigned long : 1;
+ unsigned long asteo : 25; /* ASN-Second-Table-Entry Origin */
+ unsigned long : 6;
+ unsigned long astesn : 32; /* ASTE Sequence Number */
+} __packed;
+
+struct aste {
+ unsigned long i : 1; /* ASX-Invalid Bit */
+ unsigned long ato : 29; /* Authority-Table Origin */
+ unsigned long : 1;
+ unsigned long b : 1; /* Base-Space Bit */
+ unsigned long ax : 16; /* Authorization Index */
+ unsigned long atl : 12; /* Authority-Table Length */
+ unsigned long : 2;
+ unsigned long ca : 1; /* Controlled-ASN Bit */
+ unsigned long ra : 1; /* Reusable-ASN Bit */
+ unsigned long asce : 64; /* Address-Space-Control Element */
+ unsigned long ald : 32;
+ unsigned long astesn : 32;
+ /* .. more fields there */
+} __packed;
int ipte_lock_held(struct kvm_vcpu *vcpu)
{
@@ -216,48 +263,48 @@ int ipte_lock_held(struct kvm_vcpu *vcpu)
if (vcpu->arch.sie_block->eca & 1)
return ic->kh != 0;
- return ipte_lock_count != 0;
+ return vcpu->kvm->arch.ipte_lock_count != 0;
}
static void ipte_lock_simple(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- mutex_lock(&ipte_mutex);
- ipte_lock_count++;
- if (ipte_lock_count > 1)
+ mutex_lock(&vcpu->kvm->arch.ipte_mutex);
+ vcpu->kvm->arch.ipte_lock_count++;
+ if (vcpu->kvm->arch.ipte_lock_count > 1)
goto out;
ic = &vcpu->kvm->arch.sca->ipte_control;
do {
- old = ACCESS_ONCE(*ic);
+ old = READ_ONCE(*ic);
while (old.k) {
cond_resched();
- old = ACCESS_ONCE(*ic);
+ old = READ_ONCE(*ic);
}
new = old;
new.k = 1;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
out:
- mutex_unlock(&ipte_mutex);
+ mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
}
static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- mutex_lock(&ipte_mutex);
- ipte_lock_count--;
- if (ipte_lock_count)
+ mutex_lock(&vcpu->kvm->arch.ipte_mutex);
+ vcpu->kvm->arch.ipte_lock_count--;
+ if (vcpu->kvm->arch.ipte_lock_count)
goto out;
ic = &vcpu->kvm->arch.sca->ipte_control;
do {
- new = old = ACCESS_ONCE(*ic);
+ old = READ_ONCE(*ic);
+ new = old;
new.k = 0;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
- if (!ipte_lock_count)
- wake_up(&vcpu->kvm->arch.ipte_wq);
+ wake_up(&vcpu->kvm->arch.ipte_wq);
out:
- mutex_unlock(&ipte_mutex);
+ mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
}
static void ipte_lock_siif(struct kvm_vcpu *vcpu)
@@ -266,10 +313,10 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
ic = &vcpu->kvm->arch.sca->ipte_control;
do {
- old = ACCESS_ONCE(*ic);
+ old = READ_ONCE(*ic);
while (old.kg) {
cond_resched();
- old = ACCESS_ONCE(*ic);
+ old = READ_ONCE(*ic);
}
new = old;
new.k = 1;
@@ -283,7 +330,8 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
ic = &vcpu->kvm->arch.sca->ipte_control;
do {
- new = old = ACCESS_ONCE(*ic);
+ old = READ_ONCE(*ic);
+ new = old;
new.kh--;
if (!new.kh)
new.k = 0;
@@ -308,15 +356,157 @@ void ipte_unlock(struct kvm_vcpu *vcpu)
ipte_unlock_simple(vcpu);
}
-static unsigned long get_vcpu_asce(struct kvm_vcpu *vcpu)
+static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
+ int write)
+{
+ union alet alet;
+ struct ale ale;
+ struct aste aste;
+ unsigned long ald_addr, authority_table_addr;
+ union ald ald;
+ int eax, rc;
+ u8 authority_table;
+
+ if (ar >= NUM_ACRS)
+ return -EINVAL;
+
+ save_access_regs(vcpu->run->s.regs.acrs);
+ alet.val = vcpu->run->s.regs.acrs[ar];
+
+ if (ar == 0 || alet.val == 0) {
+ asce->val = vcpu->arch.sie_block->gcr[1];
+ return 0;
+ } else if (alet.val == 1) {
+ asce->val = vcpu->arch.sie_block->gcr[7];
+ return 0;
+ }
+
+ if (alet.reserved)
+ return PGM_ALET_SPECIFICATION;
+
+ if (alet.p)
+ ald_addr = vcpu->arch.sie_block->gcr[5];
+ else
+ ald_addr = vcpu->arch.sie_block->gcr[2];
+ ald_addr &= 0x7fffffc0;
+
+ rc = read_guest_real(vcpu, ald_addr + 16, &ald.val, sizeof(union ald));
+ if (rc)
+ return rc;
+
+ if (alet.alen / 8 > ald.all)
+ return PGM_ALEN_TRANSLATION;
+
+ if (0x7fffffff - ald.alo * 128 < alet.alen * 16)
+ return PGM_ADDRESSING;
+
+ rc = read_guest_real(vcpu, ald.alo * 128 + alet.alen * 16, &ale,
+ sizeof(struct ale));
+ if (rc)
+ return rc;
+
+ if (ale.i == 1)
+ return PGM_ALEN_TRANSLATION;
+ if (ale.alesn != alet.alesn)
+ return PGM_ALE_SEQUENCE;
+
+ rc = read_guest_real(vcpu, ale.asteo * 64, &aste, sizeof(struct aste));
+ if (rc)
+ return rc;
+
+ if (aste.i)
+ return PGM_ASTE_VALIDITY;
+ if (aste.astesn != ale.astesn)
+ return PGM_ASTE_SEQUENCE;
+
+ if (ale.p == 1) {
+ eax = (vcpu->arch.sie_block->gcr[8] >> 16) & 0xffff;
+ if (ale.aleax != eax) {
+ if (eax / 16 > aste.atl)
+ return PGM_EXTENDED_AUTHORITY;
+
+ authority_table_addr = aste.ato * 4 + eax / 4;
+
+ rc = read_guest_real(vcpu, authority_table_addr,
+ &authority_table,
+ sizeof(u8));
+ if (rc)
+ return rc;
+
+ if ((authority_table & (0x40 >> ((eax & 3) * 2))) == 0)
+ return PGM_EXTENDED_AUTHORITY;
+ }
+ }
+
+ if (ale.fo == 1 && write)
+ return PGM_PROTECTION;
+
+ asce->val = aste.asce;
+ return 0;
+}
+
+struct trans_exc_code_bits {
+ unsigned long addr : 52; /* Translation-exception Address */
+ unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */
+ unsigned long : 6;
+ unsigned long b60 : 1;
+ unsigned long b61 : 1;
+ unsigned long as : 2; /* ASCE Identifier */
+};
+
+enum {
+ FSI_UNKNOWN = 0, /* Unknown wether fetch or store */
+ FSI_STORE = 1, /* Exception was due to store operation */
+ FSI_FETCH = 2 /* Exception was due to fetch operation */
+};
+
+static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
+ ar_t ar, int write)
{
+ int rc;
+ psw_t *psw = &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;
+
+ if (!psw_bits(*psw).t) {
+ asce->val = 0;
+ asce->r = 1;
+ return 0;
+ }
+
switch (psw_bits(vcpu->arch.sie_block->gpsw).as) {
case PSW_AS_PRIMARY:
- return vcpu->arch.sie_block->gcr[1];
+ asce->val = vcpu->arch.sie_block->gcr[1];
+ return 0;
case PSW_AS_SECONDARY:
- return vcpu->arch.sie_block->gcr[7];
+ asce->val = vcpu->arch.sie_block->gcr[7];
+ return 0;
case PSW_AS_HOME:
- return vcpu->arch.sie_block->gcr[13];
+ asce->val = vcpu->arch.sie_block->gcr[13];
+ return 0;
+ case PSW_AS_ACCREG:
+ rc = ar_translation(vcpu, asce, ar, write);
+ switch (rc) {
+ case PGM_ALEN_TRANSLATION:
+ case PGM_ALE_SEQUENCE:
+ case PGM_ASTE_VALIDITY:
+ case PGM_ASTE_SEQUENCE:
+ case PGM_EXTENDED_AUTHORITY:
+ vcpu->arch.pgm.exc_access_id = ar;
+ break;
+ case PGM_PROTECTION:
+ tec_bits->b60 = 1;
+ tec_bits->b61 = 1;
+ break;
+ }
+ if (rc > 0)
+ pgm->code = rc;
+ return rc;
}
return 0;
}
@@ -331,10 +521,11 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
* @vcpu: virtual cpu
* @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
*
* Translate a guest virtual address into a guest absolute address by means
- * of dynamic address translation as specified by the architecuture.
+ * of dynamic address translation as specified by the architecture.
* If the resulting absolute address is not available in the configuration
* an addressing exception is indicated and @gpa will not be changed.
*
@@ -346,7 +537,8 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
* by the architecture
*/
static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
- unsigned long *gpa, int write)
+ unsigned long *gpa, const union asce asce,
+ int write)
{
union vaddress vaddr = {.addr = gva};
union raddress raddr = {.addr = gva};
@@ -355,12 +547,10 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
union ctlreg0 ctlreg0;
unsigned long ptr;
int edat1, edat2;
- union asce asce;
ctlreg0.val = vcpu->arch.sie_block->gcr[0];
- edat1 = ctlreg0.edat && test_vfacility(8);
- edat2 = edat1 && test_vfacility(78);
- asce.val = get_vcpu_asce(vcpu);
+ edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8);
+ edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78);
if (asce.r)
goto real_address;
ptr = asce.origin * 4096;
@@ -507,48 +697,30 @@ static inline int is_low_address(unsigned long ga)
return (ga & ~0x11fful) == 0;
}
-static int low_address_protection_enabled(struct kvm_vcpu *vcpu)
+static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
+ const union asce asce)
{
union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]};
psw_t *psw = &vcpu->arch.sie_block->gpsw;
- union asce asce;
if (!ctlreg0.lap)
return 0;
- asce.val = get_vcpu_asce(vcpu);
if (psw_bits(*psw).t && asce.p)
return 0;
return 1;
}
-struct trans_exc_code_bits {
- unsigned long addr : 52; /* Translation-exception Address */
- unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */
- unsigned long : 7;
- unsigned long b61 : 1;
- unsigned long as : 2; /* ASCE Identifier */
-};
-
-enum {
- FSI_UNKNOWN = 0, /* Unknown wether fetch or store */
- FSI_STORE = 1, /* Exception was due to store operation */
- FSI_FETCH = 2 /* Exception was due to fetch operation */
-};
-
static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
unsigned long *pages, unsigned long nr_pages,
- int write)
+ const union asce asce, int write)
{
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
psw_t *psw = &vcpu->arch.sie_block->gpsw;
struct trans_exc_code_bits *tec_bits;
int lap_enabled, rc;
- 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;
- lap_enabled = low_address_protection_enabled(vcpu);
+ lap_enabled = low_address_protection_enabled(vcpu, asce);
while (nr_pages) {
ga = kvm_s390_logical_to_effective(vcpu, ga);
tec_bits->addr = ga >> PAGE_SHIFT;
@@ -558,7 +730,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
}
ga &= PAGE_MASK;
if (psw_bits(*psw).t) {
- rc = guest_translate(vcpu, ga, pages, write);
+ rc = guest_translate(vcpu, ga, pages, asce, write);
if (rc < 0)
return rc;
if (rc == PGM_PROTECTION)
@@ -579,7 +751,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
return 0;
}
-int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len, int write)
{
psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -592,20 +764,19 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
if (!len)
return 0;
- /* Access register mode is not supported yet. */
- if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG)
- return -EOPNOTSUPP;
+ rc = get_vcpu_asce(vcpu, &asce, ar, write);
+ if (rc)
+ return rc;
nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
pages = pages_array;
if (nr_pages > ARRAY_SIZE(pages_array))
pages = vmalloc(nr_pages * sizeof(unsigned long));
if (!pages)
return -ENOMEM;
- asce.val = get_vcpu_asce(vcpu);
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, write);
+ rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write);
for (idx = 0; idx < nr_pages && !rc; idx++) {
gpa = *(pages + idx) + (ga & ~PAGE_MASK);
_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
@@ -653,7 +824,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
* Note: The IPTE lock is not taken during this function, so the caller
* has to take care of this.
*/
-int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
+int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
unsigned long *gpa, int write)
{
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
@@ -662,26 +833,21 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
union asce asce;
int rc;
- /* Access register mode is not supported yet. */
- if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG)
- return -EOPNOTSUPP;
-
gva = kvm_s390_logical_to_effective(vcpu, gva);
- memset(pgm, 0, sizeof(*pgm));
tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
- tec->as = psw_bits(*psw).as;
- tec->fsi = write ? FSI_STORE : FSI_FETCH;
+ rc = get_vcpu_asce(vcpu, &asce, ar, write);
tec->addr = gva >> PAGE_SHIFT;
- if (is_low_address(gva) && low_address_protection_enabled(vcpu)) {
+ if (rc)
+ return rc;
+ if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
if (write) {
rc = pgm->code = PGM_PROTECTION;
return rc;
}
}
- asce.val = get_vcpu_asce(vcpu);
if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */
- rc = guest_translate(vcpu, gva, gpa, write);
+ rc = guest_translate(vcpu, gva, gpa, asce, write);
if (rc > 0) {
if (rc == PGM_PROTECTION)
tec->b61 = 1;
@@ -698,28 +864,51 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
}
/**
- * kvm_s390_check_low_addr_protection - check for low-address protection
- * @ga: Guest address
+ * 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 gpa;
+ unsigned long currlen;
+ int rc = 0;
+
+ 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);
+ gva += currlen;
+ length -= currlen;
+ }
+ ipte_unlock(vcpu);
+
+ return rc;
+}
+
+/**
+ * kvm_s390_check_low_addr_prot_real - check for low-address protection
+ * @gra: Guest real address
*
* Checks whether an address is subject to low-address protection and set
* up vcpu->arch.pgm accordingly if necessary.
*
* Return: 0 if no protection exception, or PGM_PROTECTION if protected.
*/
-int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga)
+int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
{
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
psw_t *psw = &vcpu->arch.sie_block->gpsw;
struct trans_exc_code_bits *tec_bits;
+ union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]};
- if (!is_low_address(ga) || !low_address_protection_enabled(vcpu))
+ if (!ctlreg0.lap || !is_low_address(gra))
return 0;
memset(pgm, 0, sizeof(*pgm));
tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
tec_bits->fsi = FSI_STORE;
tec_bits->as = psw_bits(*psw).as;
- tec_bits->addr = ga >> PAGE_SHIFT;
+ tec_bits->addr = gra >> PAGE_SHIFT;
pgm->code = PGM_PROTECTION;
return pgm->code;
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 0149cf15058a..ef03726cc661 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -156,9 +156,11 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
}
int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
- unsigned long *gpa, int write);
+ ar_t ar, unsigned long *gpa, int write);
+int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
+ unsigned long length, int is_write);
-int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len, int write);
int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
@@ -168,6 +170,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
* write_guest - copy data from kernel space to guest space
* @vcpu: virtual cpu
* @ga: guest address
+ * @ar: access register
* @data: source address in kernel space
* @len: number of bytes to copy
*
@@ -176,8 +179,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
* If DAT is off data will be copied to guest real or absolute memory.
* If DAT is on data will be copied to the address space as specified by
* the address space bits of the PSW:
- * Primary, secondory or home space (access register mode is currently not
- * implemented).
+ * Primary, secondary, home space or access register mode.
* The addressing mode of the PSW is also inspected, so that address wrap
* around is taken into account for 24-, 31- and 64-bit addressing mode,
* if the to be copied data crosses page boundaries in guest address space.
@@ -210,16 +212,17 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
* if data has been changed in guest space in case of an exception.
*/
static inline __must_check
-int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len)
{
- return access_guest(vcpu, ga, data, len, 1);
+ return access_guest(vcpu, ga, ar, data, len, 1);
}
/**
* read_guest - copy data from guest space to kernel space
* @vcpu: virtual cpu
* @ga: guest address
+ * @ar: access register
* @data: destination address in kernel space
* @len: number of bytes to copy
*
@@ -229,10 +232,10 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
* data will be copied from guest space to kernel space.
*/
static inline __must_check
-int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len)
{
- return access_guest(vcpu, ga, data, len, 0);
+ return access_guest(vcpu, ga, ar, data, len, 0);
}
/**
@@ -330,6 +333,6 @@ int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
void ipte_lock(struct kvm_vcpu *vcpu);
void ipte_unlock(struct kvm_vcpu *vcpu);
int ipte_lock_held(struct kvm_vcpu *vcpu);
-int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga);
+int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra);
#endif /* __KVM_S390_GACCESS_H */
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 3e8d4092ce30..e97b3455d7e6 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -191,8 +191,8 @@ static int __import_wp_info(struct kvm_vcpu *vcpu,
if (!wp_info->old_data)
return -ENOMEM;
/* try to backup the original value */
- ret = read_guest(vcpu, wp_info->phys_addr, wp_info->old_data,
- wp_info->len);
+ ret = read_guest_abs(vcpu, wp_info->phys_addr, wp_info->old_data,
+ wp_info->len);
if (ret) {
kfree(wp_info->old_data);
wp_info->old_data = NULL;
@@ -362,8 +362,8 @@ static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu)
continue;
/* refetch the wp data and compare it to the old value */
- if (!read_guest(vcpu, wp_info->phys_addr, temp,
- wp_info->len)) {
+ if (!read_guest_abs(vcpu, wp_info->phys_addr, temp,
+ wp_info->len)) {
if (memcmp(temp, wp_info->old_data, wp_info->len)) {
kfree(temp);
return wp_info;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index a0b586c1913c..9e3779e3e496 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -38,6 +38,19 @@ static const intercept_handler_t instruction_handlers[256] = {
[0xeb] = kvm_s390_handle_eb,
};
+void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
+{
+ struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+
+ /* Use the length of the EXECUTE instruction if necessary */
+ if (sie_block->icptstatus & 1) {
+ ilc = (sie_block->icptstatus >> 4) & 0x6;
+ if (!ilc)
+ ilc = 4;
+ }
+ sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc);
+}
+
static int handle_noop(struct kvm_vcpu *vcpu)
{
switch (vcpu->arch.sie_block->icptcode) {
@@ -55,33 +68,36 @@ static int handle_noop(struct kvm_vcpu *vcpu)
static int handle_stop(struct kvm_vcpu *vcpu)
{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc = 0;
+ uint8_t flags, stop_pending;
vcpu->stat.exit_stop_request++;
- spin_lock_bh(&vcpu->arch.local_int.lock);
- trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits);
+ /* delay the stop if any non-stop irq is pending */
+ if (kvm_s390_vcpu_has_irq(vcpu, 1))
+ return 0;
- if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
- kvm_s390_vcpu_stop(vcpu);
- vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
- VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
- rc = -EOPNOTSUPP;
- }
+ /* avoid races with the injection/SIGP STOP code */
+ spin_lock(&li->lock);
+ flags = li->irq.stop.flags;
+ stop_pending = kvm_s390_is_stop_irq_pending(vcpu);
+ spin_unlock(&li->lock);
- if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
- vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
- /* store status must be called unlocked. Since local_int.lock
- * only protects local_int.* and not guest memory we can give
- * up the lock here */
- spin_unlock_bh(&vcpu->arch.local_int.lock);
+ trace_kvm_s390_stop_request(stop_pending, flags);
+ if (!stop_pending)
+ return 0;
+
+ if (flags & KVM_S390_STOP_FLAG_STORE_STATUS) {
rc = kvm_s390_vcpu_store_status(vcpu,
KVM_S390_STORE_STATUS_NOADDR);
- if (rc >= 0)
- rc = -EOPNOTSUPP;
- } else
- spin_unlock_bh(&vcpu->arch.local_int.lock);
- return rc;
+ if (rc)
+ return rc;
+ }
+
+ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+ kvm_s390_vcpu_stop(vcpu);
+ return -EOPNOTSUPP;
}
static int handle_validity(struct kvm_vcpu *vcpu)
@@ -149,6 +165,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
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;
break;
@@ -250,7 +267,7 @@ static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
static int handle_external_interrupt(struct kvm_vcpu *vcpu)
{
u16 eic = vcpu->arch.sie_block->eic;
- struct kvm_s390_interrupt irq;
+ struct kvm_s390_irq irq;
psw_t newpsw;
int rc;
@@ -272,11 +289,13 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
irq.type = KVM_S390_INT_CPU_TIMER;
break;
case EXT_IRQ_EXTERNAL_CALL:
- if (kvm_s390_si_ext_call_pending(vcpu))
- return 0;
irq.type = KVM_S390_INT_EXTERNAL_CALL;
- irq.parm = vcpu->arch.sie_block->extcpuaddr;
- break;
+ irq.u.extcall.code = vcpu->arch.sie_block->extcpuaddr;
+ rc = kvm_s390_inject_vcpu(vcpu, &irq);
+ /* ignore if another external call is already pending */
+ if (rc == -EBUSY)
+ return 0;
+ return rc;
default:
return -EOPNOTSUPP;
}
@@ -294,29 +313,30 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
*/
static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
{
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
unsigned long srcaddr, dstaddr;
int reg1, reg2, rc;
kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
/* Make sure that the source is paged-in */
- srcaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg2]);
- if (kvm_is_error_gpa(vcpu->kvm, srcaddr))
- return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
+ reg2, &srcaddr, 0);
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
if (rc != 0)
return rc;
/* Make sure that the destination is paged-in */
- dstaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg1]);
- if (kvm_is_error_gpa(vcpu->kvm, dstaddr))
- return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
+ reg1, &dstaddr, 1);
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
if (rc != 0)
return rc;
- psw->addr = __rewind_psw(*psw, 4);
+ kvm_s390_rewind_psw(vcpu, 4);
return 0;
}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 90c8de22a2a0..9de47265ef73 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1,7 +1,7 @@
/*
* handling kvm guest interrupts
*
- * Copyright IBM Corp. 2008,2014
+ * Copyright IBM Corp. 2008, 2015
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License (version 2 only)
@@ -16,8 +16,13 @@
#include <linux/mmu_context.h>
#include <linux/signal.h>
#include <linux/slab.h>
+#include <linux/bitmap.h>
+#include <linux/vmalloc.h>
#include <asm/asm-offsets.h>
+#include <asm/dis.h>
#include <asm/uaccess.h>
+#include <asm/sclp.h>
+#include <asm/isc.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "trace-s390.h"
@@ -26,13 +31,9 @@
#define IOINT_SSID_MASK 0x00030000
#define IOINT_CSSID_MASK 0x03fc0000
#define IOINT_AI_MASK 0x04000000
-
-static void deliver_ckc_interrupt(struct kvm_vcpu *vcpu);
-
-static int is_ioint(u64 type)
-{
- return ((type & 0xfffe0000u) != 0xfffe0000u);
-}
+#define PFAULT_INIT 0x0600
+#define PFAULT_DONE 0x0680
+#define VIRTIO_PARAM 0x0d00
int psw_extint_disabled(struct kvm_vcpu *vcpu)
{
@@ -69,69 +70,100 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
return 1;
}
-static u64 int_word_to_isc_bits(u32 int_word)
+static int ckc_irq_pending(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.sie_block->ckc <
+ get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
+ return 0;
+ return ckc_interrupts_enabled(vcpu);
+}
+
+static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
+{
+ return !psw_extint_disabled(vcpu) &&
+ (vcpu->arch.sie_block->gcr[0] & 0x400ul);
+}
+
+static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
+{
+ return (vcpu->arch.sie_block->cputm >> 63) &&
+ cpu_timer_interrupts_enabled(vcpu);
+}
+
+static inline int is_ioirq(unsigned long irq_type)
{
- u8 isc = (int_word & 0x38000000) >> 27;
+ return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
+ (irq_type <= IRQ_PEND_IO_ISC_7));
+}
+static uint64_t isc_to_isc_bits(int isc)
+{
return (0x80 >> isc) << 24;
}
-static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
- struct kvm_s390_interrupt_info *inti)
+static inline u8 int_word_to_isc(u32 int_word)
{
- switch (inti->type) {
- case KVM_S390_INT_EXTERNAL_CALL:
- if (psw_extint_disabled(vcpu))
- return 0;
- if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
- return 1;
- case KVM_S390_INT_EMERGENCY:
- if (psw_extint_disabled(vcpu))
- return 0;
- if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
- return 1;
- return 0;
- case KVM_S390_INT_CLOCK_COMP:
- return ckc_interrupts_enabled(vcpu);
- case KVM_S390_INT_CPU_TIMER:
- if (psw_extint_disabled(vcpu))
- return 0;
- if (vcpu->arch.sie_block->gcr[0] & 0x400ul)
- return 1;
- return 0;
- case KVM_S390_INT_SERVICE:
- case KVM_S390_INT_PFAULT_INIT:
- case KVM_S390_INT_PFAULT_DONE:
- case KVM_S390_INT_VIRTIO:
- if (psw_extint_disabled(vcpu))
- return 0;
- if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
- return 1;
- return 0;
- case KVM_S390_PROGRAM_INT:
- case KVM_S390_SIGP_STOP:
- case KVM_S390_SIGP_SET_PREFIX:
- case KVM_S390_RESTART:
- return 1;
- case KVM_S390_MCHK:
- if (psw_mchk_disabled(vcpu))
- return 0;
- if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14)
- return 1;
- return 0;
- case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- if (psw_ioint_disabled(vcpu))
- return 0;
- if (vcpu->arch.sie_block->gcr[6] &
- int_word_to_isc_bits(inti->io.io_int_word))
- return 1;
- return 0;
- default:
- printk(KERN_WARNING "illegal interrupt type %llx\n",
- inti->type);
- BUG();
- }
- return 0;
+ return (int_word & 0x38000000) >> 27;
+}
+
+static inline unsigned long pending_floating_irqs(struct kvm_vcpu *vcpu)
+{
+ return vcpu->kvm->arch.float_int.pending_irqs;
+}
+
+static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.local_int.pending_irqs;
+}
+
+static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
+ unsigned long active_mask)
+{
+ int i;
+
+ for (i = 0; i <= MAX_ISC; i++)
+ if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i)))
+ active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i));
+
+ return active_mask;
+}
+
+static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
+{
+ unsigned long active_mask;
+
+ active_mask = pending_local_irqs(vcpu);
+ active_mask |= pending_floating_irqs(vcpu);
+
+ if (psw_extint_disabled(vcpu))
+ active_mask &= ~IRQ_PEND_EXT_MASK;
+ if (psw_ioint_disabled(vcpu))
+ active_mask &= ~IRQ_PEND_IO_MASK;
+ else
+ active_mask = disable_iscs(vcpu, active_mask);
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul))
+ __clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask);
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul))
+ __clear_bit(IRQ_PEND_EXT_EMERGENCY, &active_mask);
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+ __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask);
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul))
+ __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask);
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
+ __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
+ if (psw_mchk_disabled(vcpu))
+ active_mask &= ~IRQ_PEND_MCHK_MASK;
+ if (!(vcpu->arch.sie_block->gcr[14] &
+ vcpu->kvm->arch.float_int.mchk.cr14))
+ __clear_bit(IRQ_PEND_MCHK_REP, &active_mask);
+
+ /*
+ * STOP irqs will never be actively delivered. They are triggered via
+ * intercept requests and cleared when the stop intercept is performed.
+ */
+ __clear_bit(IRQ_PEND_SIGP_STOP, &active_mask);
+
+ return active_mask;
}
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
@@ -165,50 +197,320 @@ static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
}
-static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
- struct kvm_s390_interrupt_info *inti)
+static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
{
- switch (inti->type) {
- case KVM_S390_INT_EXTERNAL_CALL:
- case KVM_S390_INT_EMERGENCY:
- case KVM_S390_INT_SERVICE:
- case KVM_S390_INT_PFAULT_INIT:
- case KVM_S390_INT_PFAULT_DONE:
- case KVM_S390_INT_VIRTIO:
- case KVM_S390_INT_CLOCK_COMP:
- case KVM_S390_INT_CPU_TIMER:
- if (psw_extint_disabled(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_EXT_INT);
- else
- vcpu->arch.sie_block->lctl |= LCTL_CR0;
- break;
- case KVM_S390_SIGP_STOP:
+ if (!(pending_floating_irqs(vcpu) & IRQ_PEND_IO_MASK))
+ return;
+ else if (psw_ioint_disabled(vcpu))
+ __set_cpuflag(vcpu, CPUSTAT_IO_INT);
+ else
+ vcpu->arch.sie_block->lctl |= LCTL_CR6;
+}
+
+static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
+{
+ if (!(pending_local_irqs(vcpu) & IRQ_PEND_EXT_MASK))
+ return;
+ if (psw_extint_disabled(vcpu))
+ __set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+ else
+ vcpu->arch.sie_block->lctl |= LCTL_CR0;
+}
+
+static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu)
+{
+ if (!(pending_local_irqs(vcpu) & IRQ_PEND_MCHK_MASK))
+ return;
+ if (psw_mchk_disabled(vcpu))
+ vcpu->arch.sie_block->ictl |= ICTL_LPSW;
+ else
+ vcpu->arch.sie_block->lctl |= LCTL_CR14;
+}
+
+static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
+{
+ if (kvm_s390_is_stop_irq_pending(vcpu))
__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
- break;
- case KVM_S390_MCHK:
- if (psw_mchk_disabled(vcpu))
- vcpu->arch.sie_block->ictl |= ICTL_LPSW;
- else
- vcpu->arch.sie_block->lctl |= LCTL_CR14;
- break;
- case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- if (psw_ioint_disabled(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_IO_INT);
- else
- vcpu->arch.sie_block->lctl |= LCTL_CR6;
- break;
+}
+
+/* Set interception request for non-deliverable interrupts */
+static void set_intercept_indicators(struct kvm_vcpu *vcpu)
+{
+ set_intercept_indicators_io(vcpu);
+ set_intercept_indicators_ext(vcpu);
+ set_intercept_indicators_mchk(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:
- BUG();
+ return 0;
}
}
-static int __deliver_prog_irq(struct kvm_vcpu *vcpu,
- struct kvm_s390_pgm_info *pgm_info)
+static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ int rc;
+
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
+ 0, 0);
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
+ (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
+ return rc ? -EFAULT : 0;
+}
+
+static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ int rc;
+
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
+ 0, 0);
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP,
+ (u16 __user *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
+ return rc ? -EFAULT : 0;
+}
+
+static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_ext_info ext;
+ int rc;
+
+ spin_lock(&li->lock);
+ ext = li->irq.ext;
+ clear_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
+ li->irq.ext.ext_params2 = 0;
+ spin_unlock(&li->lock);
+
+ VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx",
+ 0, ext.ext_params2);
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ KVM_S390_INT_PFAULT_INIT,
+ 0, ext.ext_params2);
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *) __LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, PFAULT_INIT, (u16 *) __LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2);
+ return rc ? -EFAULT : 0;
+}
+
+static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
{
- const unsigned short table[] = { 2, 4, 4, 6 };
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_mchk_info mchk = {};
+ unsigned long adtl_status_addr;
+ int deliver = 0;
int rc = 0;
- switch (pgm_info->code & ~PGM_PER) {
+ spin_lock(&fi->lock);
+ spin_lock(&li->lock);
+ if (test_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs) ||
+ test_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs)) {
+ /*
+ * If there was an exigent machine check pending, then any
+ * repressible machine checks that might have been pending
+ * are indicated along with it, so always clear bits for
+ * repressible and exigent interrupts
+ */
+ mchk = li->irq.mchk;
+ clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs);
+ clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs);
+ memset(&li->irq.mchk, 0, sizeof(mchk));
+ deliver = 1;
+ }
+ /*
+ * We indicate floating repressible conditions along with
+ * other pending conditions. Channel Report Pending and Channel
+ * Subsystem damage are the only two and and are indicated by
+ * bits in mcic and masked in cr14.
+ */
+ if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) {
+ mchk.mcic |= fi->mchk.mcic;
+ mchk.cr14 |= fi->mchk.cr14;
+ memset(&fi->mchk, 0, sizeof(mchk));
+ deliver = 1;
+ }
+ spin_unlock(&li->lock);
+ spin_unlock(&fi->lock);
+
+ if (deliver) {
+ VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
+ mchk.mcic);
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ KVM_S390_MCHK,
+ mchk.cr14, mchk.mcic);
+
+ rc = kvm_s390_vcpu_store_status(vcpu,
+ KVM_S390_STORE_STATUS_PREFIXED);
+ rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR,
+ &adtl_status_addr,
+ sizeof(unsigned long));
+ rc |= kvm_s390_vcpu_store_adtl_status(vcpu,
+ adtl_status_addr);
+ rc |= put_guest_lc(vcpu, mchk.mcic,
+ (u64 __user *) __LC_MCCK_CODE);
+ rc |= put_guest_lc(vcpu, mchk.failing_storage_address,
+ (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA,
+ &mchk.fixed_logout,
+ sizeof(mchk.fixed_logout));
+ rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ }
+ return rc ? -EFAULT : 0;
+}
+
+static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ int rc;
+
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
+ vcpu->stat.deliver_restart_signal++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
+
+ rc = write_guest_lc(vcpu,
+ offsetof(struct _lowcore, restart_old_psw),
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
+ return rc ? -EFAULT : 0;
+}
+
+static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_prefix_info prefix;
+
+ spin_lock(&li->lock);
+ prefix = li->irq.prefix;
+ li->irq.prefix.address = 0;
+ clear_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
+ spin_unlock(&li->lock);
+
+ VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address);
+ vcpu->stat.deliver_prefix_signal++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ KVM_S390_SIGP_SET_PREFIX,
+ prefix.address, 0);
+
+ kvm_s390_set_prefix(vcpu, prefix.address);
+ return 0;
+}
+
+static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ int rc;
+ int cpu_addr;
+
+ spin_lock(&li->lock);
+ cpu_addr = find_first_bit(li->sigp_emerg_pending, KVM_MAX_VCPUS);
+ clear_bit(cpu_addr, li->sigp_emerg_pending);
+ if (bitmap_empty(li->sigp_emerg_pending, KVM_MAX_VCPUS))
+ clear_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
+ spin_unlock(&li->lock);
+
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
+ vcpu->stat.deliver_emergency_signal++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
+ cpu_addr, 0);
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
+ (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ return rc ? -EFAULT : 0;
+}
+
+static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_extcall_info extcall;
+ int rc;
+
+ spin_lock(&li->lock);
+ extcall = li->irq.extcall;
+ li->irq.extcall.code = 0;
+ clear_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
+ spin_unlock(&li->lock);
+
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
+ vcpu->stat.deliver_external_call++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ KVM_S390_INT_EXTERNAL_CALL,
+ extcall.code, 0);
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
+ (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ return rc ? -EFAULT : 0;
+}
+
+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);
+
+ spin_lock(&li->lock);
+ pgm_info = li->irq.pgm;
+ clear_bit(IRQ_PEND_PROG, &li->pending_irqs);
+ memset(&li->irq.pgm, 0, sizeof(pgm_info));
+ spin_unlock(&li->lock);
+
+ VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
+ pgm_info.code, ilc);
+ vcpu->stat.deliver_program_int++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
+ pgm_info.code, 0);
+
+ switch (pgm_info.code & ~PGM_PER) {
case PGM_AFX_TRANSLATION:
case PGM_ASX_TRANSLATION:
case PGM_EX_TRANSLATION:
@@ -218,8 +520,10 @@ static int __deliver_prog_irq(struct kvm_vcpu *vcpu,
case PGM_LX_TRANSLATION:
case PGM_PRIMARY_AUTHORITY:
case PGM_SECONDARY_AUTHORITY:
+ nullifying = true;
+ /* fall through */
case PGM_SPACE_SWITCH:
- rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
+ rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
(u64 *)__LC_TRANS_EXC_CODE);
break;
case PGM_ALEN_TRANSLATION:
@@ -228,8 +532,9 @@ static int __deliver_prog_irq(struct kvm_vcpu *vcpu,
case PGM_ASTE_SEQUENCE:
case PGM_ASTE_VALIDITY:
case PGM_EXTENDED_AUTHORITY:
- rc = put_guest_lc(vcpu, pgm_info->exc_access_id,
+ rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
(u8 *)__LC_EXC_ACCESS_ID);
+ nullifying = true;
break;
case PGM_ASCE_TYPE:
case PGM_PAGE_TRANSLATION:
@@ -237,336 +542,286 @@ static int __deliver_prog_irq(struct kvm_vcpu *vcpu,
case PGM_REGION_SECOND_TRANS:
case PGM_REGION_THIRD_TRANS:
case PGM_SEGMENT_TRANSLATION:
- rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
+ rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
(u64 *)__LC_TRANS_EXC_CODE);
- rc |= put_guest_lc(vcpu, pgm_info->exc_access_id,
+ rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
(u8 *)__LC_EXC_ACCESS_ID);
- rc |= put_guest_lc(vcpu, pgm_info->op_access_id,
+ rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
(u8 *)__LC_OP_ACCESS_ID);
+ nullifying = true;
break;
case PGM_MONITOR:
- rc = put_guest_lc(vcpu, pgm_info->mon_class_nr,
- (u64 *)__LC_MON_CLASS_NR);
- rc |= put_guest_lc(vcpu, pgm_info->mon_code,
+ rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
+ (u16 *)__LC_MON_CLASS_NR);
+ rc |= put_guest_lc(vcpu, pgm_info.mon_code,
(u64 *)__LC_MON_CODE);
break;
+ case PGM_VECTOR_PROCESSING:
case PGM_DATA:
- rc = put_guest_lc(vcpu, pgm_info->data_exc_code,
+ rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
(u32 *)__LC_DATA_EXC_CODE);
break;
case PGM_PROTECTION:
- rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
+ rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
(u64 *)__LC_TRANS_EXC_CODE);
- rc |= put_guest_lc(vcpu, pgm_info->exc_access_id,
+ rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
(u8 *)__LC_EXC_ACCESS_ID);
break;
+ case PGM_STACK_FULL:
+ case PGM_STACK_EMPTY:
+ case PGM_STACK_SPECIFICATION:
+ case PGM_STACK_TYPE:
+ case PGM_STACK_OPERATION:
+ case PGM_TRACE_TABEL:
+ case PGM_CRYPTO_OPERATION:
+ nullifying = true;
+ break;
}
- if (pgm_info->code & PGM_PER) {
- rc |= put_guest_lc(vcpu, pgm_info->per_code,
+ if (pgm_info.code & PGM_PER) {
+ rc |= put_guest_lc(vcpu, pgm_info.per_code,
(u8 *) __LC_PER_CODE);
- rc |= put_guest_lc(vcpu, pgm_info->per_atmid,
+ rc |= put_guest_lc(vcpu, pgm_info.per_atmid,
(u8 *)__LC_PER_ATMID);
- rc |= put_guest_lc(vcpu, pgm_info->per_address,
+ rc |= put_guest_lc(vcpu, pgm_info.per_address,
(u64 *) __LC_PER_ADDRESS);
- rc |= put_guest_lc(vcpu, pgm_info->per_access_id,
+ rc |= put_guest_lc(vcpu, pgm_info.per_access_id,
(u8 *) __LC_PER_ACCESS_ID);
}
- 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 */
- rc |= put_guest_lc(vcpu, table[vcpu->arch.sie_block->ipa >> 14],
- (u16 *) __LC_PGM_ILC);
- break;
- case ICPT_PROGI:
- rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->pgmilc,
- (u16 *) __LC_PGM_ILC);
- break;
- default:
- rc |= put_guest_lc(vcpu, 0,
- (u16 *) __LC_PGM_ILC);
- }
+ if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
+ kvm_s390_rewind_psw(vcpu, ilc);
- rc |= put_guest_lc(vcpu, pgm_info->code,
+ rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
+ rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
+ (u64 *) __LC_LAST_BREAK);
+ rc |= put_guest_lc(vcpu, pgm_info.code,
(u16 *)__LC_PGM_INT_CODE);
rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ return rc ? -EFAULT : 0;
+}
- return rc;
+static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct kvm_s390_ext_info ext;
+ int rc = 0;
+
+ spin_lock(&fi->lock);
+ if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) {
+ spin_unlock(&fi->lock);
+ return 0;
+ }
+ ext = fi->srv_signal;
+ memset(&fi->srv_signal, 0, sizeof(ext));
+ clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+
+ VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
+ ext.ext_params);
+ vcpu->stat.deliver_service_signal++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
+ ext.ext_params, 0);
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= put_guest_lc(vcpu, ext.ext_params,
+ (u32 *)__LC_EXT_PARAMS);
+
+ return rc ? -EFAULT : 0;
}
-static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
- struct kvm_s390_interrupt_info *inti)
+static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
{
- const unsigned short table[] = { 2, 4, 4, 6 };
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct kvm_s390_interrupt_info *inti;
int rc = 0;
- switch (inti->type) {
- case KVM_S390_INT_EMERGENCY:
- VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
- vcpu->stat.deliver_emergency_signal++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->emerg.code, 0);
- rc = put_guest_lc(vcpu, 0x1201, (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, inti->emerg.code,
- (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- break;
- case KVM_S390_INT_EXTERNAL_CALL:
- VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
- vcpu->stat.deliver_external_call++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->extcall.code, 0);
- rc = put_guest_lc(vcpu, 0x1202, (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, inti->extcall.code,
- (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- break;
- case KVM_S390_INT_CLOCK_COMP:
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->ext.ext_params, 0);
- deliver_ckc_interrupt(vcpu);
- break;
- case KVM_S390_INT_CPU_TIMER:
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->ext.ext_params, 0);
- rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
- (u16 *)__LC_EXT_INT_CODE);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= put_guest_lc(vcpu, inti->ext.ext_params,
- (u32 *)__LC_EXT_PARAMS);
- break;
- case KVM_S390_INT_SERVICE:
- VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
- inti->ext.ext_params);
- vcpu->stat.deliver_service_signal++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->ext.ext_params, 0);
- rc = put_guest_lc(vcpu, 0x2401, (u16 *)__LC_EXT_INT_CODE);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= put_guest_lc(vcpu, inti->ext.ext_params,
- (u32 *)__LC_EXT_PARAMS);
- break;
- case KVM_S390_INT_PFAULT_INIT:
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
- inti->ext.ext_params2);
- rc = put_guest_lc(vcpu, 0x2603, (u16 *) __LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0x0600, (u16 *) __LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
- (u64 *) __LC_EXT_PARAMS2);
- break;
- case KVM_S390_INT_PFAULT_DONE:
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
- inti->ext.ext_params2);
- rc = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0x0680, (u16 *)__LC_EXT_CPU_ADDR);
+ spin_lock(&fi->lock);
+ inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_PFAULT],
+ struct kvm_s390_interrupt_info,
+ list);
+ if (inti) {
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ KVM_S390_INT_PFAULT_DONE, 0,
+ inti->ext.ext_params2);
+ list_del(&inti->list);
+ fi->counters[FIRQ_CNTR_PFAULT] -= 1;
+ }
+ if (list_empty(&fi->lists[FIRQ_LIST_PFAULT]))
+ clear_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+
+ if (inti) {
+ rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE,
+ (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, PFAULT_DONE,
+ (u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
- (u64 *)__LC_EXT_PARAMS2);
- break;
- case KVM_S390_INT_VIRTIO:
- VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
+ (u64 *)__LC_EXT_PARAMS2);
+ kfree(inti);
+ }
+ return rc ? -EFAULT : 0;
+}
+
+static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct kvm_s390_interrupt_info *inti;
+ int rc = 0;
+
+ spin_lock(&fi->lock);
+ inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_VIRTIO],
+ struct kvm_s390_interrupt_info,
+ list);
+ if (inti) {
+ VCPU_EVENT(vcpu, 4,
+ "interrupt: virtio parm:%x,parm64:%llx",
inti->ext.ext_params, inti->ext.ext_params2);
vcpu->stat.deliver_virtio_interrupt++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->ext.ext_params,
- inti->ext.ext_params2);
- rc = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0x0d00, (u16 *)__LC_EXT_CPU_ADDR);
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ inti->type,
+ inti->ext.ext_params,
+ inti->ext.ext_params2);
+ list_del(&inti->list);
+ fi->counters[FIRQ_CNTR_VIRTIO] -= 1;
+ }
+ if (list_empty(&fi->lists[FIRQ_LIST_VIRTIO]))
+ clear_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+
+ if (inti) {
+ rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE,
+ (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, VIRTIO_PARAM,
+ (u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
rc |= put_guest_lc(vcpu, inti->ext.ext_params,
- (u32 *)__LC_EXT_PARAMS);
+ (u32 *)__LC_EXT_PARAMS);
rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
- (u64 *)__LC_EXT_PARAMS2);
- break;
- case KVM_S390_SIGP_STOP:
- VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
- vcpu->stat.deliver_stop_signal++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- 0, 0);
- __set_intercept_indicator(vcpu, inti);
- break;
-
- case KVM_S390_SIGP_SET_PREFIX:
- VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
- inti->prefix.address);
- vcpu->stat.deliver_prefix_signal++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->prefix.address, 0);
- kvm_s390_set_prefix(vcpu, inti->prefix.address);
- break;
+ (u64 *)__LC_EXT_PARAMS2);
+ kfree(inti);
+ }
+ return rc ? -EFAULT : 0;
+}
- case KVM_S390_RESTART:
- VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
- vcpu->stat.deliver_restart_signal++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- 0, 0);
- rc = write_guest_lc(vcpu,
- offsetof(struct _lowcore, restart_old_psw),
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- break;
- case KVM_S390_PROGRAM_INT:
- VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
- inti->pgm.code,
- table[vcpu->arch.sie_block->ipa >> 14]);
- vcpu->stat.deliver_program_int++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->pgm.code, 0);
- rc = __deliver_prog_irq(vcpu, &inti->pgm);
- break;
+static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
+ unsigned long irq_type)
+{
+ struct list_head *isc_list;
+ struct kvm_s390_float_interrupt *fi;
+ struct kvm_s390_interrupt_info *inti = NULL;
+ int rc = 0;
- case KVM_S390_MCHK:
- VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
- inti->mchk.mcic);
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- inti->mchk.cr14,
- inti->mchk.mcic);
- rc = kvm_s390_vcpu_store_status(vcpu,
- KVM_S390_STORE_STATUS_PREFIXED);
- rc |= put_guest_lc(vcpu, inti->mchk.mcic, (u64 *)__LC_MCCK_CODE);
- rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- break;
+ fi = &vcpu->kvm->arch.float_int;
- case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- {
- __u32 param0 = ((__u32)inti->io.subchannel_id << 16) |
- inti->io.subchannel_nr;
- __u64 param1 = ((__u64)inti->io.io_int_parm << 32) |
- inti->io.io_int_word;
+ spin_lock(&fi->lock);
+ isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0];
+ inti = list_first_entry_or_null(isc_list,
+ struct kvm_s390_interrupt_info,
+ list);
+ if (inti) {
VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
vcpu->stat.deliver_io_int++;
- trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
- param0, param1);
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ inti->type,
+ ((__u32)inti->io.subchannel_id << 16) |
+ inti->io.subchannel_nr,
+ ((__u64)inti->io.io_int_parm << 32) |
+ inti->io.io_int_word);
+ list_del(&inti->list);
+ fi->counters[FIRQ_CNTR_IO] -= 1;
+ }
+ if (list_empty(isc_list))
+ clear_bit(irq_type, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+
+ if (inti) {
rc = put_guest_lc(vcpu, inti->io.subchannel_id,
- (u16 *)__LC_SUBCHANNEL_ID);
+ (u16 *)__LC_SUBCHANNEL_ID);
rc |= put_guest_lc(vcpu, inti->io.subchannel_nr,
- (u16 *)__LC_SUBCHANNEL_NR);
+ (u16 *)__LC_SUBCHANNEL_NR);
rc |= put_guest_lc(vcpu, inti->io.io_int_parm,
- (u32 *)__LC_IO_INT_PARM);
+ (u32 *)__LC_IO_INT_PARM);
rc |= put_guest_lc(vcpu, inti->io.io_int_word,
- (u32 *)__LC_IO_INT_WORD);
+ (u32 *)__LC_IO_INT_WORD);
rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- break;
- }
- default:
- BUG();
- }
- if (rc) {
- printk("kvm: The guest lowcore is not mapped during interrupt "
- "delivery, killing userspace\n");
- do_exit(SIGKILL);
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ kfree(inti);
}
-}
-
-static void deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
-{
- int rc;
- rc = put_guest_lc(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- if (rc) {
- printk("kvm: The guest lowcore is not mapped during interrupt "
- "delivery, killing userspace\n");
- do_exit(SIGKILL);
- }
+ return rc ? -EFAULT : 0;
}
-/* Check whether SIGP interpretation facility has an external call pending */
-int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu)
+typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);
+
+static const deliver_irq_t deliver_irq_funcs[] = {
+ [IRQ_PEND_MCHK_EX] = __deliver_machine_check,
+ [IRQ_PEND_MCHK_REP] = __deliver_machine_check,
+ [IRQ_PEND_PROG] = __deliver_prog,
+ [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal,
+ [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call,
+ [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc,
+ [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer,
+ [IRQ_PEND_RESTART] = __deliver_restart,
+ [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix,
+ [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init,
+ [IRQ_PEND_EXT_SERVICE] = __deliver_service,
+ [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done,
+ [IRQ_PEND_VIRTIO] = __deliver_virtio,
+};
+
+/* Check whether an external call is pending (deliverable or not) */
+int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
{
- atomic_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl;
+ 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 (!psw_extint_disabled(vcpu) &&
- (vcpu->arch.sie_block->gcr[0] & 0x2000ul) &&
- (atomic_read(sigp_ctrl) & SIGP_CTRL_C) &&
- (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
- return 1;
+ if (!sclp_has_sigpif())
+ return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
- return 0;
+ return (sigp_ctrl & SIGP_CTRL_C) &&
+ (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
}
-int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
{
- struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
- struct kvm_s390_interrupt_info *inti;
- int rc = 0;
-
- if (atomic_read(&li->active)) {
- spin_lock_bh(&li->lock);
- list_for_each_entry(inti, &li->list, list)
- if (__interrupt_is_deliverable(vcpu, inti)) {
- rc = 1;
- break;
- }
- spin_unlock_bh(&li->lock);
- }
+ int rc;
- if ((!rc) && atomic_read(&fi->active)) {
- spin_lock(&fi->lock);
- list_for_each_entry(inti, &fi->list, list)
- if (__interrupt_is_deliverable(vcpu, inti)) {
- rc = 1;
- break;
- }
- spin_unlock(&fi->lock);
- }
+ rc = !!deliverable_irqs(vcpu);
if (!rc && kvm_cpu_has_pending_timer(vcpu))
rc = 1;
- if (!rc && kvm_s390_si_ext_call_pending(vcpu))
+ /* external call pending and deliverable */
+ if (!rc && kvm_s390_ext_call_pending(vcpu) &&
+ !psw_extint_disabled(vcpu) &&
+ (vcpu->arch.sie_block->gcr[0] & 0x2000ul))
+ rc = 1;
+
+ if (!rc && !exclude_stop && kvm_s390_is_stop_irq_pending(vcpu))
rc = 1;
return rc;
@@ -574,254 +829,166 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
- if (!(vcpu->arch.sie_block->ckc <
- get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
- return 0;
- if (!ckc_interrupts_enabled(vcpu))
- return 0;
- return 1;
+ return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
}
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
u64 now, sltime;
- DECLARE_WAITQUEUE(wait, current);
vcpu->stat.exit_wait_state++;
- if (kvm_cpu_has_interrupt(vcpu))
- return 0;
- __set_cpu_idle(vcpu);
- spin_lock_bh(&vcpu->arch.local_int.lock);
- vcpu->arch.local_int.timer_due = 0;
- spin_unlock_bh(&vcpu->arch.local_int.lock);
+ /* fast path */
+ if (kvm_cpu_has_pending_timer(vcpu) || kvm_arch_vcpu_runnable(vcpu))
+ return 0;
if (psw_interrupts_disabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
- __unset_cpu_idle(vcpu);
return -EOPNOTSUPP; /* disabled wait */
}
if (!ckc_interrupts_enabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
+ __set_cpu_idle(vcpu);
goto no_timer;
}
now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
- if (vcpu->arch.sie_block->ckc < now) {
- __unset_cpu_idle(vcpu);
- return 0;
- }
-
sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+ /* underflow */
+ if (vcpu->arch.sie_block->ckc < now)
+ return 0;
+
+ __set_cpu_idle(vcpu);
hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
no_timer:
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
- spin_lock(&vcpu->arch.local_int.float_int->lock);
- spin_lock_bh(&vcpu->arch.local_int.lock);
- add_wait_queue(&vcpu->wq, &wait);
- while (list_empty(&vcpu->arch.local_int.list) &&
- list_empty(&vcpu->arch.local_int.float_int->list) &&
- (!vcpu->arch.local_int.timer_due) &&
- !signal_pending(current) &&
- !kvm_s390_si_ext_call_pending(vcpu)) {
- set_current_state(TASK_INTERRUPTIBLE);
- spin_unlock_bh(&vcpu->arch.local_int.lock);
- spin_unlock(&vcpu->arch.local_int.float_int->lock);
- schedule();
- spin_lock(&vcpu->arch.local_int.float_int->lock);
- spin_lock_bh(&vcpu->arch.local_int.lock);
- }
+ kvm_vcpu_block(vcpu);
__unset_cpu_idle(vcpu);
- __set_current_state(TASK_RUNNING);
- remove_wait_queue(&vcpu->wq, &wait);
- spin_unlock_bh(&vcpu->arch.local_int.lock);
- spin_unlock(&vcpu->arch.local_int.float_int->lock);
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
+ hrtimer_cancel(&vcpu->arch.ckc_timer);
return 0;
}
-void kvm_s390_tasklet(unsigned long parm)
+void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm;
-
- spin_lock(&vcpu->arch.local_int.lock);
- vcpu->arch.local_int.timer_due = 1;
- if (waitqueue_active(&vcpu->wq))
+ if (waitqueue_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);
- spin_unlock(&vcpu->arch.local_int.lock);
+ vcpu->stat.halt_wakeup++;
+ }
}
-/*
- * low level hrtimer wake routine. Because this runs in hardirq context
- * we schedule a tasklet to do the real work.
- */
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
struct kvm_vcpu *vcpu;
+ u64 now, sltime;
vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
- vcpu->preempted = true;
- tasklet_schedule(&vcpu->arch.tasklet);
+ now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
+ sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+ /*
+ * 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)))
+ return HRTIMER_RESTART;
+ kvm_s390_vcpu_wakeup(vcpu);
return HRTIMER_NORESTART;
}
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- struct kvm_s390_interrupt_info *n, *inti = NULL;
- spin_lock_bh(&li->lock);
- list_for_each_entry_safe(inti, n, &li->list, list) {
- list_del(&inti->list);
- kfree(inti);
- }
- atomic_set(&li->active, 0);
- spin_unlock_bh(&li->lock);
+ spin_lock(&li->lock);
+ li->pending_irqs = 0;
+ bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS);
+ memset(&li->irq, 0, sizeof(li->irq));
+ spin_unlock(&li->lock);
/* clear pending external calls set by sigp interpretation facility */
- atomic_clear_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
- atomic_clear_mask(SIGP_CTRL_C,
- &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl);
+ atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags);
+ vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
}
-void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
+int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
- struct kvm_s390_interrupt_info *n, *inti = NULL;
- int deliver;
+ deliver_irq_t func;
+ int rc = 0;
+ unsigned long irq_type;
+ unsigned long irqs;
__reset_intercept_indicators(vcpu);
- if (atomic_read(&li->active)) {
- do {
- deliver = 0;
- 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);
- deliver = 1;
- break;
- }
- __set_intercept_indicator(vcpu, inti);
- }
- if (list_empty(&li->list))
- atomic_set(&li->active, 0);
- spin_unlock_bh(&li->lock);
- if (deliver) {
- __do_deliver_interrupt(vcpu, inti);
- kfree(inti);
+
+ /* pending ckc conditions might have been invalidated */
+ clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
+ if (ckc_irq_pending(vcpu))
+ set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
+
+ /* pending cpu timer conditions might have been invalidated */
+ clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
+ if (cpu_timer_irq_pending(vcpu))
+ set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
+
+ do {
+ irqs = deliverable_irqs(vcpu);
+ /* bits are in the order of interrupt priority */
+ irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
+ if (irq_type == IRQ_PEND_COUNT)
+ break;
+ if (is_ioirq(irq_type)) {
+ rc = __deliver_io(vcpu, irq_type);
+ } else {
+ func = deliver_irq_funcs[irq_type];
+ if (!func) {
+ WARN_ON_ONCE(func == NULL);
+ clear_bit(irq_type, &li->pending_irqs);
+ continue;
}
- } while (deliver);
- }
+ rc = func(vcpu);
+ }
+ if (rc)
+ break;
+ } while (!rc);
- if (kvm_cpu_has_pending_timer(vcpu))
- deliver_ckc_interrupt(vcpu);
+ set_intercept_indicators(vcpu);
- if (atomic_read(&fi->active)) {
- do {
- deliver = 0;
- spin_lock(&fi->lock);
- list_for_each_entry_safe(inti, n, &fi->list, list) {
- if (__interrupt_is_deliverable(vcpu, inti)) {
- list_del(&inti->list);
- fi->irq_count--;
- deliver = 1;
- break;
- }
- __set_intercept_indicator(vcpu, inti);
- }
- if (list_empty(&fi->list))
- atomic_set(&fi->active, 0);
- spin_unlock(&fi->lock);
- if (deliver) {
- __do_deliver_interrupt(vcpu, inti);
- kfree(inti);
- }
- } while (deliver);
- }
+ return rc;
}
-void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
+static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
- struct kvm_s390_interrupt_info *n, *inti = NULL;
- int deliver;
-
- __reset_intercept_indicators(vcpu);
- if (atomic_read(&li->active)) {
- do {
- deliver = 0;
- spin_lock_bh(&li->lock);
- 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);
- deliver = 1;
- break;
- }
- __set_intercept_indicator(vcpu, inti);
- }
- if (list_empty(&li->list))
- atomic_set(&li->active, 0);
- spin_unlock_bh(&li->lock);
- if (deliver) {
- __do_deliver_interrupt(vcpu, inti);
- kfree(inti);
- }
- } while (deliver);
- }
- if (atomic_read(&fi->active)) {
- do {
- deliver = 0;
- spin_lock(&fi->lock);
- 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);
- fi->irq_count--;
- deliver = 1;
- break;
- }
- __set_intercept_indicator(vcpu, inti);
- }
- if (list_empty(&fi->list))
- atomic_set(&fi->active, 0);
- spin_unlock(&fi->lock);
- if (deliver) {
- __do_deliver_interrupt(vcpu, inti);
- kfree(inti);
- }
- } while (deliver);
- }
+ li->irq.pgm = irq->u.pgm;
+ set_bit(IRQ_PEND_PROG, &li->pending_irqs);
+ return 0;
}
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- struct kvm_s390_interrupt_info *inti;
-
- inti = kzalloc(sizeof(*inti), GFP_KERNEL);
- if (!inti)
- return -ENOMEM;
-
- inti->type = KVM_S390_PROGRAM_INT;
- inti->pgm.code = code;
+ struct kvm_s390_irq irq;
VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
- trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1);
- spin_lock_bh(&li->lock);
- list_add(&inti->list, &li->list);
- atomic_set(&li->active, 1);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code,
+ 0, 1);
+ spin_lock(&li->lock);
+ irq.u.pgm.code = code;
+ __inject_prog(vcpu, &irq);
BUG_ON(waitqueue_active(li->wq));
- spin_unlock_bh(&li->lock);
+ spin_unlock(&li->lock);
return 0;
}
@@ -829,101 +996,383 @@ int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
struct kvm_s390_pgm_info *pgm_info)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- struct kvm_s390_interrupt_info *inti;
-
- inti = kzalloc(sizeof(*inti), GFP_KERNEL);
- if (!inti)
- return -ENOMEM;
+ struct kvm_s390_irq irq;
+ int rc;
VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)",
pgm_info->code);
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info->code, 0, 1);
-
- inti->type = KVM_S390_PROGRAM_INT;
- memcpy(&inti->pgm, pgm_info, sizeof(inti->pgm));
- spin_lock_bh(&li->lock);
- list_add(&inti->list, &li->list);
- atomic_set(&li->active, 1);
+ spin_lock(&li->lock);
+ irq.u.pgm = *pgm_info;
+ rc = __inject_prog(vcpu, &irq);
BUG_ON(waitqueue_active(li->wq));
- spin_unlock_bh(&li->lock);
+ spin_unlock(&li->lock);
+ return rc;
+}
+
+static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+ VCPU_EVENT(vcpu, 3, "inject: external irq params:%x, params2:%llx",
+ irq->u.ext.ext_params, irq->u.ext.ext_params2);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
+ irq->u.ext.ext_params,
+ irq->u.ext.ext_params2, 2);
+
+ li->irq.ext = irq->u.ext;
+ set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ 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_set_mask(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;
+ struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
+ uint16_t src_id = irq->u.extcall.code;
+
+ VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
+ src_id);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
+ src_id, 0, 2);
+
+ /* sending vcpu invalid */
+ if (src_id >= KVM_MAX_VCPUS ||
+ kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
+ return -EINVAL;
+
+ if (sclp_has_sigpif())
+ return __inject_extcall_sigpif(vcpu, src_id);
+
+ if (!test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
+ return -EBUSY;
+ *extcall = irq->u.extcall;
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ return 0;
+}
+
+static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
+
+ VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
+ irq->u.prefix.address);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
+ irq->u.prefix.address, 0, 2);
+
+ if (!is_vcpu_stopped(vcpu))
+ return -EBUSY;
+
+ *prefix = irq->u.prefix;
+ set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
+ return 0;
+}
+
+#define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS)
+static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_stop_info *stop = &li->irq.stop;
+ int rc = 0;
+
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2);
+
+ if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
+ return -EINVAL;
+
+ if (is_vcpu_stopped(vcpu)) {
+ if (irq->u.stop.flags & KVM_S390_STOP_FLAG_STORE_STATUS)
+ rc = kvm_s390_store_status_unloaded(vcpu,
+ KVM_S390_STORE_STATUS_NOADDR);
+ return rc;
+ }
+
+ if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs))
+ return -EBUSY;
+ stop->flags = irq->u.stop.flags;
+ __set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+ return 0;
+}
+
+static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
+ struct kvm_s390_irq *irq)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+ VCPU_EVENT(vcpu, 3, "inject: restart type %llx", irq->type);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0, 2);
+
+ set_bit(IRQ_PEND_RESTART, &li->pending_irqs);
return 0;
}
+static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
+ struct kvm_s390_irq *irq)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+ VCPU_EVENT(vcpu, 3, "inject: emergency %u\n",
+ irq->u.emerg.code);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
+ irq->u.emerg.code, 0, 2);
+
+ set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
+ set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ return 0;
+}
+
+static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
+
+ VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
+ irq->u.mchk.mcic);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
+ irq->u.mchk.mcic, 2);
+
+ /*
+ * Because repressible machine checks can be indicated along with
+ * exigent machine checks (PoP, Chapter 11, Interruption action)
+ * we need to combine cr14, mcic and external damage code.
+ * Failing storage address and the logout area should not be or'ed
+ * together, we just indicate the last occurrence of the corresponding
+ * machine check
+ */
+ mchk->cr14 |= irq->u.mchk.cr14;
+ mchk->mcic |= irq->u.mchk.mcic;
+ mchk->ext_damage_code |= irq->u.mchk.ext_damage_code;
+ mchk->failing_storage_address = irq->u.mchk.failing_storage_address;
+ memcpy(&mchk->fixed_logout, &irq->u.mchk.fixed_logout,
+ sizeof(mchk->fixed_logout));
+ if (mchk->mcic & MCHK_EX_MASK)
+ set_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs);
+ else if (mchk->mcic & MCHK_REP_MASK)
+ set_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs);
+ return 0;
+}
+
+static int __inject_ckc(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+ VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CLOCK_COMP);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
+ 0, 0, 2);
+
+ set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ return 0;
+}
+
+static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+ VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CPU_TIMER);
+ trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
+ 0, 0, 2);
+
+ set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ return 0;
+}
+
+static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm,
+ int isc, u32 schid)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ struct list_head *isc_list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
+ struct kvm_s390_interrupt_info *iter;
+ u16 id = (schid & 0xffff0000U) >> 16;
+ u16 nr = schid & 0x0000ffffU;
+
+ spin_lock(&fi->lock);
+ list_for_each_entry(iter, isc_list, list) {
+ if (schid && (id != iter->io.subchannel_id ||
+ nr != iter->io.subchannel_nr))
+ continue;
+ /* found an appropriate entry */
+ list_del_init(&iter->list);
+ fi->counters[FIRQ_CNTR_IO] -= 1;
+ if (list_empty(isc_list))
+ clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+ return iter;
+ }
+ spin_unlock(&fi->lock);
+ return NULL;
+}
+
+/*
+ * Dequeue and return an I/O interrupt matching any of the interruption
+ * subclasses as designated by the isc mask in cr6 and the schid (if != 0).
+ */
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
- u64 cr6, u64 schid)
+ u64 isc_mask, u32 schid)
+{
+ struct kvm_s390_interrupt_info *inti = NULL;
+ int isc;
+
+ for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
+ if (isc_mask & isc_to_isc_bits(isc))
+ inti = get_io_int(kvm, isc, schid);
+ }
+ return inti;
+}
+
+#define SCCB_MASK 0xFFFFFFF8
+#define SCCB_EVENT_PENDING 0x3
+
+static int __inject_service(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+
+ spin_lock(&fi->lock);
+ fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING;
+ /*
+ * Early versions of the QEMU s390 bios will inject several
+ * service interrupts after another without handling a
+ * condition code indicating busy.
+ * We will silently ignore those superfluous sccb values.
+ * A future version of QEMU will take care of serialization
+ * of servc requests
+ */
+ if (fi->srv_signal.ext_params & SCCB_MASK)
+ goto out;
+ fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_MASK;
+ set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
+out:
+ spin_unlock(&fi->lock);
+ kfree(inti);
+ return 0;
+}
+
+static int __inject_virtio(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+
+ spin_lock(&fi->lock);
+ if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) {
+ spin_unlock(&fi->lock);
+ return -EBUSY;
+ }
+ fi->counters[FIRQ_CNTR_VIRTIO] += 1;
+ list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_VIRTIO]);
+ set_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+ return 0;
+}
+
+static int __inject_pfault_done(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+
+ spin_lock(&fi->lock);
+ if (fi->counters[FIRQ_CNTR_PFAULT] >=
+ (ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) {
+ spin_unlock(&fi->lock);
+ return -EBUSY;
+ }
+ fi->counters[FIRQ_CNTR_PFAULT] += 1;
+ list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_PFAULT]);
+ set_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+ return 0;
+}
+
+#define CR_PENDING_SUBCLASS 28
+static int __inject_float_mchk(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+
+ spin_lock(&fi->lock);
+ fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS);
+ fi->mchk.mcic |= inti->mchk.mcic;
+ set_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+ kfree(inti);
+ return 0;
+}
+
+static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
{
struct kvm_s390_float_interrupt *fi;
- struct kvm_s390_interrupt_info *inti, *iter;
+ struct list_head *list;
+ int isc;
- if ((!schid && !cr6) || (schid && cr6))
- return NULL;
- 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 &&
- ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
- continue;
- if (schid) {
- if (((schid & 0x00000000ffff0000) >> 16) !=
- iter->io.subchannel_id)
- continue;
- if ((schid & 0x000000000000ffff) !=
- iter->io.subchannel_nr)
- continue;
- }
- inti = iter;
- break;
- }
- if (inti) {
- list_del_init(&inti->list);
- fi->irq_count--;
+ if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) {
+ spin_unlock(&fi->lock);
+ return -EBUSY;
}
- if (list_empty(&fi->list))
- atomic_set(&fi->active, 0);
+ fi->counters[FIRQ_CNTR_IO] += 1;
+
+ isc = int_word_to_isc(inti->io.io_int_word);
+ list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
+ list_add_tail(&inti->list, list);
+ set_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
spin_unlock(&fi->lock);
- mutex_unlock(&kvm->lock);
- return inti;
+ return 0;
}
static int __inject_vm(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 *iter;
struct kvm_vcpu *dst_vcpu = NULL;
int sigcpu;
- int rc = 0;
+ u64 type = READ_ONCE(inti->type);
+ int rc;
- mutex_lock(&kvm->lock);
fi = &kvm->arch.float_int;
- spin_lock(&fi->lock);
- if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
+
+ switch (type) {
+ case KVM_S390_MCHK:
+ rc = __inject_float_mchk(kvm, inti);
+ break;
+ case KVM_S390_INT_VIRTIO:
+ rc = __inject_virtio(kvm, inti);
+ break;
+ case KVM_S390_INT_SERVICE:
+ rc = __inject_service(kvm, inti);
+ break;
+ case KVM_S390_INT_PFAULT_DONE:
+ rc = __inject_pfault_done(kvm, inti);
+ break;
+ case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+ rc = __inject_io(kvm, inti);
+ break;
+ default:
rc = -EINVAL;
- goto unlock_fi;
}
- fi->irq_count++;
- if (!is_ioint(inti->type)) {
- list_add_tail(&inti->list, &fi->list);
- } else {
- u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+ if (rc)
+ return rc;
- /* Keep I/O interrupts sorted in isc order. */
- list_for_each_entry(iter, &fi->list, list) {
- if (!is_ioint(iter->type))
- continue;
- if (int_word_to_isc_bits(iter->io.io_int_word)
- <= isc_bits)
- 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 {
@@ -934,22 +1383,29 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
}
dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
li = &dst_vcpu->arch.local_int;
- spin_lock_bh(&li->lock);
- atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
- if (waitqueue_active(li->wq))
- wake_up_interruptible(li->wq);
- kvm_get_vcpu(kvm, sigcpu)->preempted = true;
- spin_unlock_bh(&li->lock);
-unlock_fi:
- spin_unlock(&fi->lock);
- mutex_unlock(&kvm->lock);
- return rc;
+ spin_lock(&li->lock);
+ switch (type) {
+ case KVM_S390_MCHK:
+ atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+ break;
+ case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+ atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
+ break;
+ default:
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ break;
+ }
+ spin_unlock(&li->lock);
+ kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
+ return 0;
+
}
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)
@@ -968,7 +1424,6 @@ int kvm_s390_inject_vm(struct kvm *kvm,
inti->ext.ext_params = s390int->parm;
break;
case KVM_S390_INT_PFAULT_DONE:
- inti->type = s390int->type;
inti->ext.ext_params2 = s390int->parm64;
break;
case KVM_S390_MCHK:
@@ -997,182 +1452,235 @@ int kvm_s390_inject_vm(struct kvm *kvm,
trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
2);
- return __inject_vm(kvm, inti);
+ rc = __inject_vm(kvm, inti);
+ if (rc)
+ kfree(inti);
+ return rc;
}
-void kvm_s390_reinject_io_int(struct kvm *kvm,
+int kvm_s390_reinject_io_int(struct kvm *kvm,
struct kvm_s390_interrupt_info *inti)
{
- __inject_vm(kvm, inti);
+ return __inject_vm(kvm, inti);
}
-int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
- struct kvm_s390_interrupt *s390int)
+int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
+ struct kvm_s390_irq *irq)
{
- struct kvm_s390_local_interrupt *li;
- struct kvm_s390_interrupt_info *inti;
+ irq->type = s390int->type;
+ switch (irq->type) {
+ case KVM_S390_PROGRAM_INT:
+ if (s390int->parm & 0xffff0000)
+ return -EINVAL;
+ irq->u.pgm.code = s390int->parm;
+ break;
+ case KVM_S390_SIGP_SET_PREFIX:
+ irq->u.prefix.address = s390int->parm;
+ break;
+ case KVM_S390_SIGP_STOP:
+ irq->u.stop.flags = s390int->parm;
+ break;
+ case KVM_S390_INT_EXTERNAL_CALL:
+ if (s390int->parm & 0xffff0000)
+ return -EINVAL;
+ irq->u.extcall.code = s390int->parm;
+ break;
+ case KVM_S390_INT_EMERGENCY:
+ if (s390int->parm & 0xffff0000)
+ return -EINVAL;
+ irq->u.emerg.code = s390int->parm;
+ break;
+ case KVM_S390_MCHK:
+ irq->u.mchk.mcic = s390int->parm64;
+ break;
+ }
+ return 0;
+}
- inti = kzalloc(sizeof(*inti), GFP_KERNEL);
- if (!inti)
- return -ENOMEM;
+int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- switch (s390int->type) {
+ return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
+}
+
+void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+ spin_lock(&li->lock);
+ li->irq.stop.flags = 0;
+ clear_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
+ spin_unlock(&li->lock);
+}
+
+static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
+{
+ int rc;
+
+ switch (irq->type) {
case KVM_S390_PROGRAM_INT:
- if (s390int->parm & 0xffff0000) {
- kfree(inti);
- return -EINVAL;
- }
- inti->type = s390int->type;
- inti->pgm.code = s390int->parm;
VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
- s390int->parm);
+ irq->u.pgm.code);
+ rc = __inject_prog(vcpu, irq);
break;
case KVM_S390_SIGP_SET_PREFIX:
- inti->prefix.address = s390int->parm;
- inti->type = s390int->type;
- VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
- s390int->parm);
+ rc = __inject_set_prefix(vcpu, irq);
break;
case KVM_S390_SIGP_STOP:
+ rc = __inject_sigp_stop(vcpu, irq);
+ break;
case KVM_S390_RESTART:
+ rc = __inject_sigp_restart(vcpu, irq);
+ break;
case KVM_S390_INT_CLOCK_COMP:
+ rc = __inject_ckc(vcpu);
+ break;
case KVM_S390_INT_CPU_TIMER:
- VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
- inti->type = s390int->type;
+ rc = __inject_cpu_timer(vcpu);
break;
case KVM_S390_INT_EXTERNAL_CALL:
- if (s390int->parm & 0xffff0000) {
- kfree(inti);
- return -EINVAL;
- }
- VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
- s390int->parm);
- inti->type = s390int->type;
- inti->extcall.code = s390int->parm;
+ rc = __inject_extcall(vcpu, irq);
break;
case KVM_S390_INT_EMERGENCY:
- if (s390int->parm & 0xffff0000) {
- kfree(inti);
- return -EINVAL;
- }
- VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", s390int->parm);
- inti->type = s390int->type;
- inti->emerg.code = s390int->parm;
+ rc = __inject_sigp_emergency(vcpu, irq);
break;
case KVM_S390_MCHK:
- VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
- s390int->parm64);
- inti->type = s390int->type;
- inti->mchk.mcic = s390int->parm64;
+ rc = __inject_mchk(vcpu, irq);
break;
case KVM_S390_INT_PFAULT_INIT:
- inti->type = s390int->type;
- inti->ext.ext_params2 = s390int->parm64;
+ rc = __inject_pfault_init(vcpu, irq);
break;
case KVM_S390_INT_VIRTIO:
case KVM_S390_INT_SERVICE:
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
default:
- kfree(inti);
- return -EINVAL;
+ rc = -EINVAL;
}
- trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, s390int->type, s390int->parm,
- s390int->parm64, 2);
-
- mutex_lock(&vcpu->kvm->lock);
- li = &vcpu->arch.local_int;
- spin_lock_bh(&li->lock);
- if (inti->type == KVM_S390_PROGRAM_INT)
- list_add(&inti->list, &li->list);
- else
- list_add_tail(&inti->list, &li->list);
- atomic_set(&li->active, 1);
- if (inti->type == KVM_S390_SIGP_STOP)
- li->action_bits |= ACTION_STOP_ON_STOP;
- atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
- if (waitqueue_active(&vcpu->wq))
- wake_up_interruptible(&vcpu->wq);
- vcpu->preempted = true;
- spin_unlock_bh(&li->lock);
- mutex_unlock(&vcpu->kvm->lock);
- return 0;
+
+ return rc;
}
-void kvm_s390_clear_float_irqs(struct kvm *kvm)
+int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
{
- struct kvm_s390_float_interrupt *fi;
- struct kvm_s390_interrupt_info *n, *inti = NULL;
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ int rc;
- mutex_lock(&kvm->lock);
- fi = &kvm->arch.float_int;
- spin_lock(&fi->lock);
- list_for_each_entry_safe(inti, n, &fi->list, list) {
+ spin_lock(&li->lock);
+ rc = do_inject_vcpu(vcpu, irq);
+ spin_unlock(&li->lock);
+ if (!rc)
+ kvm_s390_vcpu_wakeup(vcpu);
+ return rc;
+}
+
+static inline void clear_irq_list(struct list_head *_list)
+{
+ struct kvm_s390_interrupt_info *inti, *n;
+
+ list_for_each_entry_safe(inti, n, _list, list) {
list_del(&inti->list);
kfree(inti);
}
- fi->irq_count = 0;
- atomic_set(&fi->active, 0);
- spin_unlock(&fi->lock);
- mutex_unlock(&kvm->lock);
}
-static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti,
- u8 *addr)
+static void inti_to_irq(struct kvm_s390_interrupt_info *inti,
+ struct kvm_s390_irq *irq)
{
- struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
- struct kvm_s390_irq irq = {0};
-
- irq.type = inti->type;
+ irq->type = inti->type;
switch (inti->type) {
case KVM_S390_INT_PFAULT_INIT:
case KVM_S390_INT_PFAULT_DONE:
case KVM_S390_INT_VIRTIO:
- case KVM_S390_INT_SERVICE:
- irq.u.ext = inti->ext;
+ irq->u.ext = inti->ext;
break;
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- irq.u.io = inti->io;
- break;
- case KVM_S390_MCHK:
- irq.u.mchk = inti->mchk;
+ irq->u.io = inti->io;
break;
- default:
- return -EINVAL;
}
+}
- if (copy_to_user(uptr, &irq, sizeof(irq)))
- return -EFAULT;
+void kvm_s390_clear_float_irqs(struct kvm *kvm)
+{
+ struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ int i;
- return 0;
-}
+ spin_lock(&fi->lock);
+ for (i = 0; i < FIRQ_LIST_COUNT; i++)
+ clear_irq_list(&fi->lists[i]);
+ for (i = 0; i < FIRQ_MAX_COUNT; i++)
+ fi->counters[i] = 0;
+ spin_unlock(&fi->lock);
+};
-static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len)
+static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
{
struct kvm_s390_interrupt_info *inti;
struct kvm_s390_float_interrupt *fi;
+ struct kvm_s390_irq *buf;
+ struct kvm_s390_irq *irq;
+ int max_irqs;
int ret = 0;
int n = 0;
+ int i;
+
+ if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0)
+ return -EINVAL;
+
+ /*
+ * We are already using -ENOMEM to signal
+ * userspace it may retry with a bigger buffer,
+ * so we need to use something else for this case
+ */
+ buf = vzalloc(len);
+ if (!buf)
+ return -ENOBUFS;
+
+ max_irqs = len / sizeof(struct kvm_s390_irq);
- mutex_lock(&kvm->lock);
fi = &kvm->arch.float_int;
spin_lock(&fi->lock);
-
- list_for_each_entry(inti, &fi->list, list) {
- if (len < sizeof(struct kvm_s390_irq)) {
+ for (i = 0; i < FIRQ_LIST_COUNT; i++) {
+ list_for_each_entry(inti, &fi->lists[i], list) {
+ if (n == max_irqs) {
+ /* signal userspace to try again */
+ ret = -ENOMEM;
+ goto out;
+ }
+ inti_to_irq(inti, &buf[n]);
+ n++;
+ }
+ }
+ if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) {
+ if (n == max_irqs) {
/* signal userspace to try again */
ret = -ENOMEM;
- break;
+ goto out;
}
- ret = copy_irq_to_user(inti, buf);
- if (ret)
- break;
- buf += sizeof(struct kvm_s390_irq);
- len -= sizeof(struct kvm_s390_irq);
+ irq = (struct kvm_s390_irq *) &buf[n];
+ irq->type = KVM_S390_INT_SERVICE;
+ irq->u.ext = fi->srv_signal;
n++;
}
+ if (test_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) {
+ if (n == max_irqs) {
+ /* signal userspace to try again */
+ ret = -ENOMEM;
+ goto out;
+ }
+ irq = (struct kvm_s390_irq *) &buf[n];
+ irq->type = KVM_S390_MCHK;
+ irq->u.mchk = fi->mchk;
+ n++;
+}
+out:
spin_unlock(&fi->lock);
- mutex_unlock(&kvm->lock);
+ if (!ret && n > 0) {
+ if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
+ ret = -EFAULT;
+ }
+ vfree(buf);
return ret < 0 ? ret : n;
}
@@ -1183,7 +1691,7 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
switch (attr->group) {
case KVM_DEV_FLIC_GET_ALL_IRQS:
- r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr,
+ r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr,
attr->attr);
break;
default:
@@ -1333,7 +1841,7 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
}
INIT_LIST_HEAD(&map->list);
map->guest_addr = addr;
- map->addr = gmap_translate(addr, kvm->arch.gmap);
+ map->addr = gmap_translate(kvm->arch.gmap, addr);
if (map->addr == -EFAULT) {
ret = -EFAULT;
goto out;
@@ -1443,7 +1951,6 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
r = enqueue_floating_irq(dev, attr);
break;
case KVM_DEV_FLIC_CLEAR_IRQS:
- r = 0;
kvm_s390_clear_float_irqs(dev->kvm);
break;
case KVM_DEV_FLIC_APF_ENABLE:
@@ -1589,8 +2096,7 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
return ret;
}
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
- struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
{
int ret;
@@ -1617,3 +2123,143 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
{
return -EINVAL;
}
+
+int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_irq *buf;
+ int r = 0;
+ int n;
+
+ buf = vmalloc(len);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user((void *) buf, irqstate, len)) {
+ r = -EFAULT;
+ goto out_free;
+ }
+
+ /*
+ * Don't allow setting the interrupt state
+ * when there are already interrupts pending
+ */
+ spin_lock(&li->lock);
+ if (li->pending_irqs) {
+ r = -EBUSY;
+ goto out_unlock;
+ }
+
+ for (n = 0; n < len / sizeof(*buf); n++) {
+ r = do_inject_vcpu(vcpu, &buf[n]);
+ if (r)
+ break;
+ }
+
+out_unlock:
+ spin_unlock(&li->lock);
+out_free:
+ vfree(buf);
+
+ return r;
+}
+
+static void store_local_irq(struct kvm_s390_local_interrupt *li,
+ struct kvm_s390_irq *irq,
+ unsigned long irq_type)
+{
+ switch (irq_type) {
+ case IRQ_PEND_MCHK_EX:
+ case IRQ_PEND_MCHK_REP:
+ irq->type = KVM_S390_MCHK;
+ irq->u.mchk = li->irq.mchk;
+ break;
+ case IRQ_PEND_PROG:
+ irq->type = KVM_S390_PROGRAM_INT;
+ irq->u.pgm = li->irq.pgm;
+ break;
+ case IRQ_PEND_PFAULT_INIT:
+ irq->type = KVM_S390_INT_PFAULT_INIT;
+ irq->u.ext = li->irq.ext;
+ break;
+ case IRQ_PEND_EXT_EXTERNAL:
+ irq->type = KVM_S390_INT_EXTERNAL_CALL;
+ irq->u.extcall = li->irq.extcall;
+ break;
+ case IRQ_PEND_EXT_CLOCK_COMP:
+ irq->type = KVM_S390_INT_CLOCK_COMP;
+ break;
+ case IRQ_PEND_EXT_CPU_TIMER:
+ irq->type = KVM_S390_INT_CPU_TIMER;
+ break;
+ case IRQ_PEND_SIGP_STOP:
+ irq->type = KVM_S390_SIGP_STOP;
+ irq->u.stop = li->irq.stop;
+ break;
+ case IRQ_PEND_RESTART:
+ irq->type = KVM_S390_RESTART;
+ break;
+ case IRQ_PEND_SET_PREFIX:
+ irq->type = KVM_S390_SIGP_SET_PREFIX;
+ irq->u.prefix = li->irq.prefix;
+ break;
+ }
+}
+
+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;
+ 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;
+ struct kvm_s390_irq irq;
+ unsigned long irq_type;
+ int cpuaddr;
+ int n = 0;
+
+ spin_lock(&li->lock);
+ pending_irqs = li->pending_irqs;
+ memcpy(&sigp_emerg_pending, &li->sigp_emerg_pending,
+ sizeof(sigp_emerg_pending));
+ spin_unlock(&li->lock);
+
+ for_each_set_bit(irq_type, &pending_irqs, IRQ_PEND_COUNT) {
+ memset(&irq, 0, sizeof(irq));
+ if (irq_type == IRQ_PEND_EXT_EMERGENCY)
+ continue;
+ if (n + sizeof(irq) > len)
+ return -ENOBUFS;
+ store_local_irq(&vcpu->arch.local_int, &irq, irq_type);
+ if (copy_to_user(&buf[n], &irq, sizeof(irq)))
+ return -EFAULT;
+ n += sizeof(irq);
+ }
+
+ if (test_bit(IRQ_PEND_EXT_EMERGENCY, &pending_irqs)) {
+ for_each_set_bit(cpuaddr, sigp_emerg_pending, KVM_MAX_VCPUS) {
+ memset(&irq, 0, sizeof(irq));
+ if (n + sizeof(irq) > len)
+ return -ENOBUFS;
+ irq.type = KVM_S390_INT_EMERGENCY;
+ irq.u.emerg.code = cpuaddr;
+ if (copy_to_user(&buf[n], &irq, sizeof(irq)))
+ return -EFAULT;
+ n += sizeof(irq);
+ }
+ }
+
+ if ((sigp_ctrl & SIGP_CTRL_C) &&
+ (atomic_read(&vcpu->arch.sie_block->cpuflags) &
+ CPUSTAT_ECALL_PEND)) {
+ 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;
+ if (copy_to_user(&buf[n], &irq, sizeof(irq)))
+ return -EFAULT;
+ n += sizeof(irq);
+ }
+
+ return n;
+}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2f3e14fe91a4..afa2bd750ffc 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -22,14 +22,16 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
+#include <linux/random.h>
#include <linux/slab.h>
#include <linux/timer.h>
+#include <linux/vmalloc.h>
#include <asm/asm-offsets.h>
#include <asm/lowcore.h>
#include <asm/pgtable.h>
#include <asm/nmi.h>
#include <asm/switch_to.h>
-#include <asm/facility.h>
+#include <asm/isc.h>
#include <asm/sclp.h>
#include "kvm-s390.h"
#include "gaccess.h"
@@ -38,6 +40,11 @@
#include "trace.h"
#include "trace-s390.h"
+#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */
+#define LOCAL_IRQS 32
+#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
+ (KVM_MAX_VCPUS + LOCAL_IRQS))
+
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
struct kvm_stats_debugfs_item debugfs_entries[] = {
@@ -50,6 +57,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "exit_instruction", VCPU_STAT(exit_instruction) },
{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
+ { "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
+ { "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
@@ -80,36 +89,45 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
+ { "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
+ { "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
+ { "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
+ { "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
+ { "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) },
{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
+ { "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
+ { "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
+ { "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
{ "diagnose_10", VCPU_STAT(diagnose_10) },
{ "diagnose_44", VCPU_STAT(diagnose_44) },
{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
{ NULL }
};
-unsigned long *vfacilities;
-static struct gmap_notifier gmap_notifier;
+/* upper facilities limit for kvm */
+unsigned long kvm_s390_fac_list_mask[] = {
+ 0xffe6fffbfcfdfc40UL,
+ 0x205c800000000000UL,
+};
-/* test availability of vfacility */
-int test_vfacility(unsigned long nr)
+unsigned long kvm_s390_fac_list_mask_size(void)
{
- return __test_facility(nr, (void *) vfacilities);
+ BUILD_BUG_ON(ARRAY_SIZE(kvm_s390_fac_list_mask) > S390_ARCH_FAC_MASK_SIZE_U64);
+ return ARRAY_SIZE(kvm_s390_fac_list_mask);
}
+static struct gmap_notifier gmap_notifier;
+
/* Section: not file related */
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
/* every s390 is virtualization enabled ;-) */
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);
int kvm_arch_hardware_setup(void)
@@ -124,17 +142,10 @@ void kvm_arch_hardware_unsetup(void)
gmap_unregister_ipte_notifier(&gmap_notifier);
}
-void kvm_arch_check_processor_compat(void *rtn)
-{
-}
-
int kvm_arch_init(void *opaque)
{
- return 0;
-}
-
-void kvm_arch_exit(void)
-{
+ /* Register floating interrupt controller interface. */
+ return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
}
/* Section: device related */
@@ -146,7 +157,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
return -EINVAL;
}
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -162,13 +173,22 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_ONE_REG:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_S390_CSS_SUPPORT:
- case KVM_CAP_IRQFD:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_ENABLE_CAP_VM:
+ case KVM_CAP_S390_IRQCHIP:
case KVM_CAP_VM_ATTRIBUTES:
+ case KVM_CAP_MP_STATE:
+ case KVM_CAP_S390_INJECT_IRQ:
+ case KVM_CAP_S390_USER_SIGP:
+ case KVM_CAP_S390_USER_STSI:
+ case KVM_CAP_S390_SKEYS:
+ case KVM_CAP_S390_IRQ_STATE:
r = 1;
break;
+ case KVM_CAP_S390_MEM_OP:
+ r = MEM_OP_MAX_SIZE;
+ break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
@@ -179,6 +199,9 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_S390_COW:
r = MACHINE_HAS_ESOP;
break;
+ case KVM_CAP_S390_VECTOR_REGISTERS:
+ r = MACHINE_HAS_VX;
+ break;
default:
r = 0;
}
@@ -255,6 +278,22 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
kvm->arch.use_irqchip = 1;
r = 0;
break;
+ case KVM_CAP_S390_USER_SIGP:
+ kvm->arch.user_sigp = 1;
+ 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);
+ r = 0;
+ } else
+ r = -EINVAL;
+ break;
+ case KVM_CAP_S390_USER_STSI:
+ kvm->arch.user_stsi = 1;
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
@@ -262,7 +301,24 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
return r;
}
-static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
+static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ int ret;
+
+ switch (attr->attr) {
+ case KVM_S390_VM_MEM_LIMIT_SIZE:
+ ret = 0;
+ if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
+ ret = -EFAULT;
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+ return ret;
+}
+
+static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
unsigned int idx;
@@ -279,11 +335,41 @@ static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_MEM_CLR_CMMA:
mutex_lock(&kvm->lock);
idx = srcu_read_lock(&kvm->srcu);
- page_table_reset_pgste(kvm->arch.gmap->mm, 0, TASK_SIZE, false);
+ s390_reset_cmma(kvm->arch.gmap->mm);
srcu_read_unlock(&kvm->srcu, idx);
mutex_unlock(&kvm->lock);
ret = 0;
break;
+ case KVM_S390_VM_MEM_LIMIT_SIZE: {
+ unsigned long new_limit;
+
+ if (kvm_is_ucontrol(kvm))
+ return -EINVAL;
+
+ if (get_user(new_limit, (u64 __user *)attr->addr))
+ return -EFAULT;
+
+ if (new_limit > kvm->arch.gmap->asce_end)
+ return -E2BIG;
+
+ ret = -EBUSY;
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus) == 0) {
+ /* gmap_alloc will round the limit up */
+ struct gmap *new = gmap_alloc(current->mm, new_limit);
+
+ if (!new) {
+ ret = -ENOMEM;
+ } else {
+ gmap_free(kvm->arch.gmap);
+ new->private = kvm;
+ kvm->arch.gmap = new;
+ ret = 0;
+ }
+ }
+ mutex_unlock(&kvm->lock);
+ break;
+ }
default:
ret = -ENXIO;
break;
@@ -291,13 +377,276 @@ static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
return ret;
}
+static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu);
+
+static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ if (!test_kvm_facility(kvm, 76))
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+ switch (attr->attr) {
+ case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
+ get_random_bytes(
+ kvm->arch.crypto.crycb->aes_wrapping_key_mask,
+ sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
+ kvm->arch.crypto.aes_kw = 1;
+ break;
+ case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
+ get_random_bytes(
+ kvm->arch.crypto.crycb->dea_wrapping_key_mask,
+ sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
+ kvm->arch.crypto.dea_kw = 1;
+ break;
+ case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
+ kvm->arch.crypto.aes_kw = 0;
+ memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
+ sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
+ break;
+ case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
+ kvm->arch.crypto.dea_kw = 0;
+ memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
+ sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
+ break;
+ default:
+ mutex_unlock(&kvm->lock);
+ return -ENXIO;
+ }
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ kvm_s390_vcpu_crypto_setup(vcpu);
+ exit_sie(vcpu);
+ }
+ mutex_unlock(&kvm->lock);
+ return 0;
+}
+
+static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ u8 gtod_high;
+
+ if (copy_from_user(&gtod_high, (void __user *)attr->addr,
+ sizeof(gtod_high)))
+ return -EFAULT;
+
+ if (gtod_high != 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_vcpu *cur_vcpu;
+ unsigned int vcpu_idx;
+ u64 host_tod, gtod;
+ int r;
+
+ if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
+ return -EFAULT;
+
+ r = store_tod_clock(&host_tod);
+ if (r)
+ return r;
+
+ mutex_lock(&kvm->lock);
+ kvm->arch.epoch = gtod - host_tod;
+ kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) {
+ cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch;
+ exit_sie(cur_vcpu);
+ }
+ mutex_unlock(&kvm->lock);
+ return 0;
+}
+
+static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ int ret;
+
+ if (attr->flags)
+ return -EINVAL;
+
+ switch (attr->attr) {
+ case KVM_S390_VM_TOD_HIGH:
+ ret = kvm_s390_set_tod_high(kvm, attr);
+ break;
+ case KVM_S390_VM_TOD_LOW:
+ ret = kvm_s390_set_tod_low(kvm, attr);
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+ return ret;
+}
+
+static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ u8 gtod_high = 0;
+
+ if (copy_to_user((void __user *)attr->addr, &gtod_high,
+ sizeof(gtod_high)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ u64 host_tod, gtod;
+ int r;
+
+ r = store_tod_clock(&host_tod);
+ if (r)
+ return r;
+
+ gtod = host_tod + kvm->arch.epoch;
+ if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ int ret;
+
+ if (attr->flags)
+ return -EINVAL;
+
+ switch (attr->attr) {
+ case KVM_S390_VM_TOD_HIGH:
+ ret = kvm_s390_get_tod_high(kvm, attr);
+ break;
+ case KVM_S390_VM_TOD_LOW:
+ ret = kvm_s390_get_tod_low(kvm, attr);
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+ return ret;
+}
+
+static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_vm_cpu_processor *proc;
+ int ret = 0;
+
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ proc = kzalloc(sizeof(*proc), GFP_KERNEL);
+ if (!proc) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ if (!copy_from_user(proc, (void __user *)attr->addr,
+ sizeof(*proc))) {
+ 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,
+ S390_ARCH_FAC_LIST_SIZE_BYTE);
+ } else
+ ret = -EFAULT;
+ kfree(proc);
+out:
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
+static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ int ret = -ENXIO;
+
+ switch (attr->attr) {
+ case KVM_S390_VM_CPU_PROCESSOR:
+ ret = kvm_s390_set_processor(kvm, attr);
+ break;
+ }
+ return ret;
+}
+
+static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_vm_cpu_processor *proc;
+ int ret = 0;
+
+ proc = kzalloc(sizeof(*proc), GFP_KERNEL);
+ if (!proc) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ 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);
+ if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
+ ret = -EFAULT;
+ kfree(proc);
+out:
+ return ret;
+}
+
+static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_vm_cpu_machine *mach;
+ int ret = 0;
+
+ mach = kzalloc(sizeof(*mach), GFP_KERNEL);
+ if (!mach) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ get_cpu_id((struct cpuid *) &mach->cpuid);
+ mach->ibc = sclp_get_ibc();
+ 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);
+ if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
+ ret = -EFAULT;
+ kfree(mach);
+out:
+ return ret;
+}
+
+static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ int ret = -ENXIO;
+
+ switch (attr->attr) {
+ case KVM_S390_VM_CPU_PROCESSOR:
+ ret = kvm_s390_get_processor(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_MACHINE:
+ ret = kvm_s390_get_machine(kvm, attr);
+ break;
+ }
+ return ret;
+}
+
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
switch (attr->group) {
case KVM_S390_VM_MEM_CTRL:
- ret = kvm_s390_mem_control(kvm, attr);
+ ret = kvm_s390_set_mem_control(kvm, attr);
+ break;
+ case KVM_S390_VM_TOD:
+ ret = kvm_s390_set_tod(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_MODEL:
+ ret = kvm_s390_set_cpu_model(kvm, attr);
+ break;
+ case KVM_S390_VM_CRYPTO:
+ ret = kvm_s390_vm_set_crypto(kvm, attr);
break;
default:
ret = -ENXIO;
@@ -309,7 +658,24 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
- return -ENXIO;
+ int ret;
+
+ switch (attr->group) {
+ case KVM_S390_VM_MEM_CTRL:
+ ret = kvm_s390_get_mem_control(kvm, attr);
+ break;
+ case KVM_S390_VM_TOD:
+ ret = kvm_s390_get_tod(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_MODEL:
+ ret = kvm_s390_get_cpu_model(kvm, attr);
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+
+ return ret;
}
static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
@@ -321,6 +687,42 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
switch (attr->attr) {
case KVM_S390_VM_MEM_ENABLE_CMMA:
case KVM_S390_VM_MEM_CLR_CMMA:
+ case KVM_S390_VM_MEM_LIMIT_SIZE:
+ ret = 0;
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+ break;
+ case KVM_S390_VM_TOD:
+ switch (attr->attr) {
+ case KVM_S390_VM_TOD_LOW:
+ case KVM_S390_VM_TOD_HIGH:
+ ret = 0;
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+ break;
+ case KVM_S390_VM_CPU_MODEL:
+ switch (attr->attr) {
+ case KVM_S390_VM_CPU_PROCESSOR:
+ case KVM_S390_VM_CPU_MACHINE:
+ ret = 0;
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+ break;
+ case KVM_S390_VM_CRYPTO:
+ switch (attr->attr) {
+ case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
+ case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
+ case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
+ case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
ret = 0;
break;
default:
@@ -336,6 +738,108 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
return ret;
}
+static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
+{
+ uint8_t *keys;
+ uint64_t hva;
+ unsigned long curkey;
+ int i, r = 0;
+
+ if (args->flags != 0)
+ return -EINVAL;
+
+ /* Is this guest using storage keys? */
+ if (!mm_use_skey(current->mm))
+ return KVM_S390_GET_SKEYS_NONE;
+
+ /* Enforce sane limit on memory allocation */
+ if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
+ return -EINVAL;
+
+ keys = kmalloc_array(args->count, sizeof(uint8_t),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!keys)
+ keys = vmalloc(sizeof(uint8_t) * args->count);
+ if (!keys)
+ return -ENOMEM;
+
+ for (i = 0; i < args->count; i++) {
+ hva = gfn_to_hva(kvm, args->start_gfn + i);
+ if (kvm_is_error_hva(hva)) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ curkey = get_guest_storage_key(current->mm, hva);
+ if (IS_ERR_VALUE(curkey)) {
+ r = curkey;
+ goto out;
+ }
+ keys[i] = curkey;
+ }
+
+ r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
+ sizeof(uint8_t) * args->count);
+ if (r)
+ r = -EFAULT;
+out:
+ kvfree(keys);
+ return r;
+}
+
+static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
+{
+ uint8_t *keys;
+ uint64_t hva;
+ int i, r = 0;
+
+ if (args->flags != 0)
+ return -EINVAL;
+
+ /* Enforce sane limit on memory allocation */
+ if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
+ return -EINVAL;
+
+ keys = kmalloc_array(args->count, sizeof(uint8_t),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!keys)
+ keys = vmalloc(sizeof(uint8_t) * args->count);
+ if (!keys)
+ return -ENOMEM;
+
+ r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr,
+ sizeof(uint8_t) * args->count);
+ if (r) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ /* Enable storage key handling for the guest */
+ s390_enable_skey();
+
+ for (i = 0; i < args->count; i++) {
+ hva = gfn_to_hva(kvm, args->start_gfn + i);
+ if (kvm_is_error_hva(hva)) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ /* Lowest order bit is reserved */
+ if (keys[i] & 0x01) {
+ r = -EINVAL;
+ goto out;
+ }
+
+ r = set_guest_storage_key(current->mm, hva,
+ (unsigned long)keys[i], 0);
+ if (r)
+ goto out;
+ }
+out:
+ kvfree(keys);
+ return r;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -395,6 +899,26 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_s390_vm_has_attr(kvm, &attr);
break;
}
+ case KVM_S390_GET_SKEYS: {
+ struct kvm_s390_skeys args;
+
+ r = -EFAULT;
+ if (copy_from_user(&args, argp,
+ sizeof(struct kvm_s390_skeys)))
+ break;
+ r = kvm_s390_get_skeys(kvm, &args);
+ break;
+ }
+ case KVM_S390_SET_SKEYS: {
+ struct kvm_s390_skeys args;
+
+ r = -EFAULT;
+ if (copy_from_user(&args, argp,
+ sizeof(struct kvm_s390_skeys)))
+ break;
+ r = kvm_s390_set_skeys(kvm, &args);
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -402,9 +926,87 @@ long kvm_arch_vm_ioctl(struct file *filp,
return r;
}
+static int kvm_s390_query_ap_config(u8 *config)
+{
+ u32 fcn_code = 0x04000000UL;
+ u32 cc = 0;
+
+ memset(config, 0, 128);
+ asm volatile(
+ "lgr 0,%1\n"
+ "lgr 2,%2\n"
+ ".long 0xb2af0000\n" /* PQAP(QCI) */
+ "0: ipm %0\n"
+ "srl %0,28\n"
+ "1:\n"
+ EX_TABLE(0b, 1b)
+ : "+r" (cc)
+ : "r" (fcn_code), "r" (config)
+ : "cc", "0", "2", "memory"
+ );
+
+ return cc;
+}
+
+static int kvm_s390_apxa_installed(void)
+{
+ u8 config[128];
+ int cc;
+
+ if (test_facility(2) && test_facility(12)) {
+ cc = kvm_s390_query_ap_config(config);
+
+ if (cc)
+ pr_err("PQAP(QCI) failed with cc=%d", cc);
+ else
+ return config[0] & 0x40;
+ }
+
+ return 0;
+}
+
+static void kvm_s390_set_crycb_format(struct kvm *kvm)
+{
+ kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb;
+
+ if (kvm_s390_apxa_installed())
+ kvm->arch.crypto.crycbd |= CRYCB_FORMAT2;
+ else
+ kvm->arch.crypto.crycbd |= CRYCB_FORMAT1;
+}
+
+static void kvm_s390_get_cpu_id(struct cpuid *cpu_id)
+{
+ get_cpu_id(cpu_id);
+ cpu_id->version = 0xff;
+}
+
+static int 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;
+
+ kvm_s390_set_crycb_format(kvm);
+
+ /* Enable AES/DEA protected key functions by default */
+ kvm->arch.crypto.aes_kw = 1;
+ kvm->arch.crypto.dea_kw = 1;
+ get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask,
+ 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;
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
- int rc;
+ int i, rc;
char debug_name[16];
static unsigned long sca_offset;
@@ -437,11 +1039,45 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
if (!kvm->arch.dbf)
- goto out_nodbf;
+ 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)
+ goto out_err;
+
+ /* Populate the facility mask initially. */
+ 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];
+ else
+ kvm->arch.model.fac->mask[i] = 0UL;
+ }
+
+ /* Populate the facility list initially. */
+ 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_get_ibc() & 0x0fff;
+
+ if (kvm_s390_crypto_init(kvm) < 0)
+ goto out_err;
spin_lock_init(&kvm->arch.float_int.lock);
- INIT_LIST_HEAD(&kvm->arch.float_int.list);
+ for (i = 0; i < FIRQ_LIST_COUNT; i++)
+ INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
init_waitqueue_head(&kvm->arch.ipte_wq);
+ mutex_init(&kvm->arch.ipte_mutex);
debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
VM_EVENT(kvm, 3, "%s", "vm created");
@@ -449,24 +1085,25 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (type & KVM_VM_S390_UCONTROL) {
kvm->arch.gmap = NULL;
} else {
- kvm->arch.gmap = gmap_alloc(current->mm);
+ kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
if (!kvm->arch.gmap)
- goto out_nogmap;
+ goto out_err;
kvm->arch.gmap->private = kvm;
kvm->arch.gmap->pfault_enabled = 0;
}
kvm->arch.css_support = 0;
kvm->arch.use_irqchip = 0;
+ kvm->arch.epoch = 0;
spin_lock_init(&kvm->arch.start_stop_lock);
return 0;
-out_nogmap:
+out_err:
+ kfree(kvm->arch.crypto.crycb);
+ free_page((unsigned long)kvm->arch.model.fac);
debug_unregister(kvm->arch.dbf);
-out_nodbf:
free_page((unsigned long)(kvm->arch.sca));
-out_err:
return rc;
}
@@ -512,15 +1149,13 @@ static void kvm_free_vcpus(struct kvm *kvm)
mutex_unlock(&kvm->lock);
}
-void kvm_arch_sync_events(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));
debug_unregister(kvm->arch.dbf);
+ kfree(kvm->arch.crypto.crycb);
if (!kvm_is_ucontrol(kvm))
gmap_free(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
@@ -528,38 +1163,50 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
}
/* Section: vcpu related */
+static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.gmap = gmap_alloc(current->mm, -1UL);
+ if (!vcpu->arch.gmap)
+ return -ENOMEM;
+ vcpu->arch.gmap->private = vcpu->kvm;
+
+ return 0;
+}
+
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
kvm_clear_async_pf_completion_queue(vcpu);
- if (kvm_is_ucontrol(vcpu->kvm)) {
- vcpu->arch.gmap = gmap_alloc(current->mm);
- if (!vcpu->arch.gmap)
- return -ENOMEM;
- vcpu->arch.gmap->private = vcpu->kvm;
- return 0;
- }
-
- vcpu->arch.gmap = vcpu->kvm->arch.gmap;
vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
KVM_SYNC_GPRS |
KVM_SYNC_ACRS |
- KVM_SYNC_CRS;
- return 0;
-}
+ KVM_SYNC_CRS |
+ KVM_SYNC_ARCH0 |
+ KVM_SYNC_PFAULT;
+ if (test_kvm_facility(vcpu->kvm, 129))
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
- /* Nothing todo */
+ if (kvm_is_ucontrol(vcpu->kvm))
+ return __kvm_ucontrol_vcpu_init(vcpu);
+
+ return 0;
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
- save_fp_regs(vcpu->arch.host_fpregs.fprs);
+ if (test_kvm_facility(vcpu->kvm, 129))
+ save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
+ else
+ save_fp_regs(vcpu->arch.host_fpregs.fprs);
save_access_regs(vcpu->arch.host_acrs);
- restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
- restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
+ if (test_kvm_facility(vcpu->kvm, 129)) {
+ restore_fp_ctl(&vcpu->run->s.regs.fpc);
+ restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
+ } else {
+ restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
+ restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
+ }
restore_access_regs(vcpu->run->s.regs.acrs);
gmap_enable(vcpu->arch.gmap);
atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
@@ -569,11 +1216,19 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
gmap_disable(vcpu->arch.gmap);
- save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
- save_fp_regs(vcpu->arch.guest_fpregs.fprs);
+ if (test_kvm_facility(vcpu->kvm, 129)) {
+ save_fp_ctl(&vcpu->run->s.regs.fpc);
+ save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
+ } else {
+ save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
+ save_fp_regs(vcpu->arch.guest_fpregs.fprs);
+ }
save_access_regs(vcpu->run->s.regs.acrs);
restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
- restore_fp_regs(vcpu->arch.host_fpregs.fprs);
+ if (test_kvm_facility(vcpu->kvm, 129))
+ restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
+ else
+ restore_fp_regs(vcpu->arch.host_fpregs.fprs);
restore_access_regs(vcpu->arch.host_acrs);
}
@@ -595,13 +1250,33 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->pp = 0;
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
kvm_clear_async_pf_completion_queue(vcpu);
- kvm_s390_vcpu_stop(vcpu);
+ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+ kvm_s390_vcpu_stop(vcpu);
kvm_s390_clear_local_irqs(vcpu);
}
-int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
- return 0;
+ mutex_lock(&vcpu->kvm->lock);
+ vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
+ mutex_unlock(&vcpu->kvm->lock);
+ if (!kvm_is_ucontrol(vcpu->kvm))
+ vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+}
+
+static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
+{
+ if (!test_kvm_facility(vcpu->kvm, 76))
+ return;
+
+ vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);
+
+ if (vcpu->kvm->arch.crypto.aes_kw)
+ vcpu->arch.sie_block->ecb3 |= ECB3_AES;
+ if (vcpu->kvm->arch.crypto.dea_kw)
+ vcpu->arch.sie_block->ecb3 |= ECB3_DEA;
+
+ vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
}
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
@@ -621,6 +1296,15 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
return 0;
}
+static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model;
+
+ vcpu->arch.cpu_id = model->cpu_id;
+ vcpu->arch.sie_block->ibc = model->ibc;
+ vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
+}
+
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
int rc = 0;
@@ -629,29 +1313,34 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
CPUSTAT_SM |
CPUSTAT_STOPPED |
CPUSTAT_GED);
+ kvm_s390_vcpu_setup_model(vcpu);
+
vcpu->arch.sie_block->ecb = 6;
- if (test_vfacility(50) && test_vfacility(73))
+ if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73))
vcpu->arch.sie_block->ecb |= 0x10;
vcpu->arch.sie_block->ecb2 = 8;
- vcpu->arch.sie_block->eca = 0xD1002000U;
+ vcpu->arch.sie_block->eca = 0xC1002000U;
if (sclp_has_siif())
vcpu->arch.sie_block->eca |= 1;
- vcpu->arch.sie_block->fac = (int) (long) vfacilities;
- vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE |
- ICTL_TPROT;
+ if (sclp_has_sigpif())
+ vcpu->arch.sie_block->eca |= 0x10000000U;
+ if (test_kvm_facility(vcpu->kvm, 129)) {
+ vcpu->arch.sie_block->eca |= 0x00020000;
+ vcpu->arch.sie_block->ecd |= 0x20000000;
+ }
+ vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
if (kvm_s390_cmma_enabled(vcpu->kvm)) {
rc = kvm_s390_vcpu_setup_cmma(vcpu);
if (rc)
return rc;
}
- hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
- tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
- (unsigned long) vcpu);
+ hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
- get_cpu_id(&vcpu->arch.cpu_id);
- vcpu->arch.cpu_id.version = 0xff;
+
+ kvm_s390_vcpu_crypto_setup(vcpu);
+
return rc;
}
@@ -677,6 +1366,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu->arch.sie_block = &sie_page->sie_block;
vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
+ vcpu->arch.host_vregs = &sie_page->vregs;
vcpu->arch.sie_block->icpua = id;
if (!kvm_is_ucontrol(kvm)) {
@@ -694,7 +1384,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
}
spin_lock_init(&vcpu->arch.local_int.lock);
- INIT_LIST_HEAD(&vcpu->arch.local_int.list);
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;
@@ -717,7 +1406,7 @@ out:
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
- return kvm_cpu_has_interrupt(vcpu);
+ return kvm_s390_vcpu_has_irq(vcpu, 0);
}
void s390_vcpu_block(struct kvm_vcpu *vcpu)
@@ -845,6 +1534,8 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
case KVM_REG_S390_PFTOKEN:
r = get_user(vcpu->arch.pfault_token,
(u64 __user *)reg->addr);
+ if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
+ kvm_clear_async_pf_completion_queue(vcpu);
break;
case KVM_REG_S390_PFCOMPARE:
r = get_user(vcpu->arch.pfault_compare,
@@ -926,7 +1617,7 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
{
int rc = 0;
- if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
+ if (!is_vcpu_stopped(vcpu))
rc = -EBUSY;
else {
vcpu->run->psw_mask = psw.mask;
@@ -980,13 +1671,34 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- return -EINVAL; /* not implemented yet */
+ /* CHECK_STOP and LOAD are not supported yet */
+ return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
+ KVM_MP_STATE_OPERATING;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- return -EINVAL; /* not implemented yet */
+ int rc = 0;
+
+ /* user space knows about this interface - let it control the state */
+ vcpu->kvm->arch.user_cpu_state_ctrl = 1;
+
+ switch (mp_state->mp_state) {
+ case KVM_MP_STATE_STOPPED:
+ kvm_s390_vcpu_stop(vcpu);
+ break;
+ case KVM_MP_STATE_OPERATING:
+ kvm_s390_vcpu_start(vcpu);
+ break;
+ case KVM_MP_STATE_LOAD:
+ case KVM_MP_STATE_CHECK_STOP:
+ /* fall through - CHECK_STOP and LOAD are not supported yet */
+ default:
+ rc = -ENXIO;
+ }
+
+ return rc;
}
bool kvm_s390_cmma_enabled(struct kvm *kvm)
@@ -1027,6 +1739,11 @@ retry:
goto retry;
}
+ if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
+ vcpu->arch.sie_block->ihcpu = 0xffff;
+ goto retry;
+ }
+
if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
if (!ibs_enabled(vcpu)) {
trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
@@ -1045,6 +1762,9 @@ retry:
goto retry;
}
+ /* nothing to do, just clear the request */
+ clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+
return 0;
}
@@ -1060,31 +1780,23 @@ retry:
*/
long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable)
{
- struct mm_struct *mm = current->mm;
- hva_t hva;
- long rc;
-
- hva = gmap_fault(gpa, vcpu->arch.gmap);
- if (IS_ERR_VALUE(hva))
- return (long)hva;
- down_read(&mm->mmap_sem);
- rc = get_user_pages(current, mm, hva, 1, writable, 0, NULL, NULL);
- up_read(&mm->mmap_sem);
-
- return rc < 0 ? rc : 0;
+ return gmap_fault(vcpu->arch.gmap, gpa,
+ writable ? FAULT_FLAG_WRITE : 0);
}
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
unsigned long token)
{
struct kvm_s390_interrupt inti;
- inti.parm64 = token;
+ struct kvm_s390_irq irq;
if (start_token) {
- inti.type = KVM_S390_INT_PFAULT_INIT;
- WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti));
+ irq.u.ext.ext_params2 = token;
+ irq.type = KVM_S390_INT_PFAULT_INIT;
+ WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
} else {
inti.type = KVM_S390_INT_PFAULT_DONE;
+ inti.parm64 = token;
WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
}
}
@@ -1131,7 +1843,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
return 0;
if (psw_extint_disabled(vcpu))
return 0;
- if (kvm_cpu_has_interrupt(vcpu))
+ if (kvm_s390_vcpu_has_irq(vcpu, 0))
return 0;
if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
return 0;
@@ -1166,8 +1878,11 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
if (test_cpu_flag(CIF_MCCK_PENDING))
s390_handle_mcck();
- if (!kvm_is_ucontrol(vcpu->kvm))
- kvm_s390_deliver_pending_interrupts(vcpu);
+ if (!kvm_is_ucontrol(vcpu->kvm)) {
+ rc = kvm_s390_deliver_pending_interrupts(vcpu);
+ if (rc)
+ return rc;
+ }
rc = kvm_s390_handle_requests(vcpu);
if (rc)
@@ -1186,6 +1901,31 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
return 0;
}
+static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
+{
+ psw_t *psw = &vcpu->arch.sie_block->gpsw;
+ u8 opcode;
+ int rc;
+
+ VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+ trace_kvm_s390_sie_fault(vcpu);
+
+ /*
+ * We want to inject an addressing exception, which is defined as a
+ * suppressing or terminating exception. However, since we came here
+ * by a DAT access exception, the PSW still points to the faulting
+ * instruction since DAT exceptions are nullifying. So we've got
+ * 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);
+}
+
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
int rc = -1;
@@ -1217,11 +1957,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
}
}
- if (rc == -1) {
- VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
- trace_kvm_s390_sie_fault(vcpu);
- rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
- }
+ if (rc == -1)
+ rc = vcpu_post_run_fault_in_sie(vcpu);
memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
@@ -1271,6 +2008,50 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
return rc;
}
+static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
+ vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+ if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
+ kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+ if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
+ memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
+ /* some control register changes require a tlb flush */
+ 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;
+ 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;
+ vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea;
+ }
+ if (kvm_run->kvm_dirty_regs & KVM_SYNC_PFAULT) {
+ vcpu->arch.pfault_token = kvm_run->s.regs.pft;
+ vcpu->arch.pfault_select = kvm_run->s.regs.pfs;
+ vcpu->arch.pfault_compare = kvm_run->s.regs.pfc;
+ if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
+ kvm_clear_async_pf_completion_queue(vcpu);
+ }
+ kvm_run->kvm_dirty_regs = 0;
+}
+
+static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask;
+ 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.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;
+ kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
+ kvm_run->s.regs.pft = vcpu->arch.pfault_token;
+ kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
+ kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+}
+
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int rc;
@@ -1284,32 +2065,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
- kvm_s390_vcpu_start(vcpu);
-
- switch (kvm_run->exit_reason) {
- case KVM_EXIT_S390_SIEIC:
- case KVM_EXIT_UNKNOWN:
- case KVM_EXIT_INTR:
- case KVM_EXIT_S390_RESET:
- case KVM_EXIT_S390_UCONTROL:
- case KVM_EXIT_S390_TSCH:
- case KVM_EXIT_DEBUG:
- break;
- default:
- BUG();
+ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
+ kvm_s390_vcpu_start(vcpu);
+ } else if (is_vcpu_stopped(vcpu)) {
+ pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n",
+ vcpu->vcpu_id);
+ return -EINVAL;
}
- vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
- vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
- if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) {
- kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
- kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
- }
- if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
- kvm_run->kvm_dirty_regs &= ~KVM_SYNC_CRS;
- memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
- kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
- }
+ sync_regs(vcpu, kvm_run);
might_fault();
rc = __vcpu_run(vcpu);
@@ -1339,10 +2103,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
rc = 0;
}
- kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask;
- 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);
+ store_regs(vcpu, kvm_run);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
@@ -1413,9 +2174,33 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
return kvm_s390_store_status_unloaded(vcpu, addr);
}
-static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
+/*
+ * store additional status at address
+ */
+int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
+ unsigned long gpa)
+{
+ /* Only bits 0-53 are used for address formation */
+ if (!(gpa & ~0x3ff))
+ return 0;
+
+ return write_guest_abs(vcpu, gpa & ~0x3ff,
+ (void *)&vcpu->run->s.regs.vrs, 512);
+}
+
+int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
{
- return atomic_read(&(vcpu)->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
+ if (!test_kvm_facility(vcpu->kvm, 129))
+ return 0;
+
+ /*
+ * The guest VXRS are in the host VXRs due to the lazy
+ * copying in vcpu load/put. Let's update our copies before we save
+ * it into the save area.
+ */
+ save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
+
+ return kvm_s390_store_adtl_status_unloaded(vcpu, addr);
}
static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
@@ -1451,7 +2236,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
/* Only one cpu at a time may enter/leave the STOPPED state. */
- spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
+ spin_lock(&vcpu->kvm->arch.start_stop_lock);
online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
for (i = 0; i < online_vcpus; i++) {
@@ -1476,8 +2261,8 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
* Another VCPU might have used IBS while we were offline.
* Let's play safe and flush the VCPU at startup.
*/
- vcpu->arch.sie_block->ihcpu = 0xffff;
- spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ spin_unlock(&vcpu->kvm->arch.start_stop_lock);
return;
}
@@ -1491,9 +2276,12 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
/* Only one cpu at a time may enter/leave the STOPPED state. */
- spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
+ spin_lock(&vcpu->kvm->arch.start_stop_lock);
online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
+ /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+ kvm_s390_clear_stop_irq(vcpu);
+
atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
__disable_ibs_on_vcpu(vcpu);
@@ -1512,7 +2300,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
__enable_ibs_on_vcpu(started_vcpu);
}
- spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
+ spin_unlock(&vcpu->kvm->arch.start_stop_lock);
return;
}
@@ -1539,6 +2327,65 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
return r;
}
+static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
+ struct kvm_s390_mem_op *mop)
+{
+ void __user *uaddr = (void __user *)mop->buf;
+ void *tmpbuf = NULL;
+ int r, srcu_idx;
+ const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
+ | KVM_S390_MEMOP_F_CHECK_ONLY;
+
+ if (mop->flags & ~supported_flags)
+ return -EINVAL;
+
+ if (mop->size > MEM_OP_MAX_SIZE)
+ return -E2BIG;
+
+ if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
+ tmpbuf = vmalloc(mop->size);
+ if (!tmpbuf)
+ return -ENOMEM;
+ }
+
+ srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+ 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);
+ break;
+ }
+ r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
+ if (r == 0) {
+ if (copy_to_user(uaddr, tmpbuf, mop->size))
+ r = -EFAULT;
+ }
+ 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);
+ break;
+ }
+ if (copy_from_user(tmpbuf, uaddr, mop->size)) {
+ r = -EFAULT;
+ break;
+ }
+ r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
+ break;
+ default:
+ r = -EINVAL;
+ }
+
+ srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+
+ if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0)
+ kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+
+ vfree(tmpbuf);
+ return r;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -1548,13 +2395,25 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
long r;
switch (ioctl) {
+ case KVM_S390_IRQ: {
+ struct kvm_s390_irq s390irq;
+
+ r = -EFAULT;
+ if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
+ break;
+ r = kvm_s390_inject_vcpu(vcpu, &s390irq);
+ break;
+ }
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
+ struct kvm_s390_irq s390irq;
r = -EFAULT;
if (copy_from_user(&s390int, argp, sizeof(s390int)))
break;
- r = kvm_s390_inject_vcpu(vcpu, &s390int);
+ if (s390int_to_s390irq(&s390int, &s390irq))
+ return -EINVAL;
+ r = kvm_s390_inject_vcpu(vcpu, &s390irq);
break;
}
case KVM_S390_STORE_STATUS:
@@ -1623,9 +2482,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
}
#endif
case KVM_S390_VCPU_FAULT: {
- r = gmap_fault(arg, vcpu->arch.gmap);
- if (!IS_ERR_VALUE(r))
- r = 0;
+ r = gmap_fault(vcpu->arch.gmap, arg, 0);
break;
}
case KVM_ENABLE_CAP:
@@ -1637,6 +2494,47 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
break;
}
+ case KVM_S390_MEM_OP: {
+ struct kvm_s390_mem_op mem_op;
+
+ if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0)
+ r = kvm_s390_guest_mem_op(vcpu, &mem_op);
+ else
+ r = -EFAULT;
+ break;
+ }
+ case KVM_S390_SET_IRQ_STATE: {
+ struct kvm_s390_irq_state irq_state;
+
+ r = -EFAULT;
+ if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
+ break;
+ if (irq_state.len > VCPU_IRQS_MAX_BUF ||
+ irq_state.len == 0 ||
+ irq_state.len % sizeof(struct kvm_s390_irq) > 0) {
+ r = -EINVAL;
+ break;
+ }
+ r = kvm_s390_set_irq_state(vcpu,
+ (void __user *) irq_state.buf,
+ irq_state.len);
+ break;
+ }
+ case KVM_S390_GET_IRQ_STATE: {
+ struct kvm_s390_irq_state irq_state;
+
+ r = -EFAULT;
+ if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
+ break;
+ if (irq_state.len == 0) {
+ r = -EINVAL;
+ break;
+ }
+ r = kvm_s390_get_irq_state(vcpu,
+ (__u8 __user *) irq_state.buf,
+ irq_state.len);
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -1656,21 +2554,12 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
-void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
- struct kvm_memory_slot *dont)
-{
-}
-
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
unsigned long npages)
{
return 0;
}
-void kvm_arch_memslots_updated(struct kvm *kvm)
-{
-}
-
/* Section: memory related */
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
@@ -1716,41 +2605,13 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
return;
}
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
- struct kvm_memory_slot *slot)
-{
-}
-
static int __init kvm_s390_init(void)
{
- int ret;
- ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
- if (ret)
- return ret;
-
- /*
- * guests can ask for up to 255+1 double words, we need a full page
- * to hold the maximum amount of facilities. On the other hand, we
- * only set facilities that are known to work in KVM.
- */
- vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
- if (!vfacilities) {
- kvm_exit();
- return -ENOMEM;
- }
- memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
- vfacilities[0] &= 0xff82fff3f4fc2000UL;
- vfacilities[1] &= 0x005c000000000000UL;
- return 0;
+ return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
}
static void __exit kvm_s390_exit(void)
{
- free_page((unsigned long) vfacilities);
kvm_exit();
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index a8655ed31616..ca108b90ae56 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -18,14 +18,10 @@
#include <linux/hrtimer.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <asm/facility.h>
typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
-/* declare vfacilities extern */
-extern unsigned long *vfacilities;
-
-int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
-
/* Transactional Memory Execution related macros */
#define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & 0x10))
#define TDB_FORMAT1 1
@@ -45,9 +41,9 @@ do { \
d_args); \
} while (0)
-static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
+static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
{
- return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
+ return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
}
static inline int kvm_is_ucontrol(struct kvm *kvm)
@@ -70,20 +66,26 @@ static inline u32 kvm_s390_get_prefix(struct kvm_vcpu *vcpu)
static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
{
vcpu->arch.sie_block->prefix = prefix >> GUEST_PREFIX_SHIFT;
- vcpu->arch.sie_block->ihcpu = 0xffff;
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
}
-static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu)
+typedef u8 __bitwise ar_t;
+
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar)
{
u32 base2 = vcpu->arch.sie_block->ipb >> 28;
u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ if (ar)
+ *ar = base2;
+
return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
}
static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
- u64 *address1, u64 *address2)
+ u64 *address1, u64 *address2,
+ ar_t *ar_b1, ar_t *ar_b2)
{
u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
@@ -92,6 +94,11 @@ static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
*address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
*address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+
+ if (ar_b1)
+ *ar_b1 = base1;
+ if (ar_b2)
+ *ar_b2 = base2;
}
static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2)
@@ -102,7 +109,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2
*r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
}
-static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar)
{
u32 base2 = vcpu->arch.sie_block->ipb >> 28;
u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
@@ -111,14 +118,20 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
if (disp2 & 0x80000)
disp2+=0xfff00000;
+ if (ar)
+ *ar = base2;
+
return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2;
}
-static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu)
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar)
{
u32 base2 = vcpu->arch.sie_block->ipb >> 28;
u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ if (ar)
+ *ar = base2;
+
return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
}
@@ -129,24 +142,51 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
vcpu->arch.sie_block->gpsw.mask |= cc << 44;
}
+/* 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);
+}
+
+static inline int set_kvm_facility(u64 *fac_list, unsigned long nr)
+{
+ unsigned char *ptr;
+
+ if (nr >= MAX_FACILITY_BIT)
+ return -EINVAL;
+ ptr = (unsigned char *) fac_list + (nr >> 3);
+ *ptr |= (0x80UL >> (nr & 7));
+ return 0;
+}
+
+/* are cpu states controlled by user space */
+static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
+{
+ return kvm->arch.user_cpu_state_ctrl != 0;
+}
+
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu);
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
-void kvm_s390_tasklet(unsigned long parm);
-void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
-void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
+int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu);
void kvm_s390_clear_float_irqs(struct kvm *kvm);
int __must_check kvm_s390_inject_vm(struct kvm *kvm,
struct kvm_s390_interrupt *s390int);
int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
- struct kvm_s390_interrupt *s390int);
+ struct kvm_s390_irq *irq);
int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
- u64 cr6, u64 schid);
-void kvm_s390_reinject_io_int(struct kvm *kvm,
- struct kvm_s390_interrupt_info *inti);
+ u64 isc_mask, u32 schid);
+int kvm_s390_reinject_io_int(struct kvm *kvm,
+ struct kvm_s390_interrupt_info *inti);
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);
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+
/* implemented in priv.c */
int is_valid_psw(psw_t *psw);
int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
@@ -165,7 +205,10 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
/* implemented in kvm-s390.c */
long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
+int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
+ unsigned long addr);
int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
+int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr);
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
void s390_vcpu_block(struct kvm_vcpu *vcpu);
@@ -176,7 +219,8 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
/* is cmma enabled */
bool kvm_s390_cmma_enabled(struct kvm *kvm);
-int test_vfacility(unsigned long nr);
+unsigned long kvm_s390_fac_list_mask_size(void);
+extern unsigned long kvm_s390_fac_list_mask[];
/* implemented in diag.c */
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
@@ -217,11 +261,21 @@ static inline int kvm_s390_inject_prog_cond(struct kvm_vcpu *vcpu, int rc)
return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
}
+int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
+ struct kvm_s390_irq *s390irq);
+
/* implemented in interrupt.c */
-int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop);
int psw_extint_disabled(struct kvm_vcpu *vcpu);
void kvm_s390_destroy_adapters(struct kvm *kvm);
-int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu);
+int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu);
+extern struct kvm_device_ops kvm_flic_ops;
+int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu);
+void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu);
+int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
+ void __user *buf, int len);
+int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu,
+ __u8 __user *buf, int len);
/* implemented in guestdbg.c */
void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index f89c1cd67751..d22d8ee1ff9d 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -36,15 +36,16 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
struct kvm_vcpu *cpup;
s64 hostclk, val;
int i, rc;
+ ar_t ar;
u64 op2;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- op2 = kvm_s390_get_base_disp_s(vcpu);
+ op2 = kvm_s390_get_base_disp_s(vcpu, &ar);
if (op2 & 7) /* Operand must be on a doubleword boundary */
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- rc = read_guest(vcpu, op2, &val, sizeof(val));
+ rc = read_guest(vcpu, op2, ar, &val, sizeof(val));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
@@ -68,20 +69,21 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
u64 operand2;
u32 address;
int rc;
+ ar_t ar;
vcpu->stat.instruction_spx++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- operand2 = kvm_s390_get_base_disp_s(vcpu);
+ operand2 = kvm_s390_get_base_disp_s(vcpu, &ar);
/* must be word boundary */
if (operand2 & 3)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
/* get the value */
- rc = read_guest(vcpu, operand2, &address, sizeof(address));
+ rc = read_guest(vcpu, operand2, ar, &address, sizeof(address));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
@@ -107,13 +109,14 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
u64 operand2;
u32 address;
int rc;
+ ar_t ar;
vcpu->stat.instruction_stpx++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- operand2 = kvm_s390_get_base_disp_s(vcpu);
+ operand2 = kvm_s390_get_base_disp_s(vcpu, &ar);
/* must be word boundary */
if (operand2 & 3)
@@ -122,7 +125,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
address = kvm_s390_get_prefix(vcpu);
/* get the value */
- rc = write_guest(vcpu, operand2, &address, sizeof(address));
+ rc = write_guest(vcpu, operand2, ar, &address, sizeof(address));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
@@ -136,18 +139,19 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
u16 vcpu_id = vcpu->vcpu_id;
u64 ga;
int rc;
+ ar_t ar;
vcpu->stat.instruction_stap++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- ga = kvm_s390_get_base_disp_s(vcpu);
+ ga = kvm_s390_get_base_disp_s(vcpu, &ar);
if (ga & 1)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- rc = write_guest(vcpu, ga, &vcpu_id, sizeof(vcpu_id));
+ rc = write_guest(vcpu, ga, ar, &vcpu_id, sizeof(vcpu_id));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
@@ -156,41 +160,42 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
return 0;
}
-static void __skey_check_enable(struct kvm_vcpu *vcpu)
+static int __skey_check_enable(struct kvm_vcpu *vcpu)
{
+ int rc = 0;
if (!(vcpu->arch.sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)))
- return;
+ return rc;
- s390_enable_skey();
+ rc = s390_enable_skey();
trace_kvm_s390_skey_related_inst(vcpu);
vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
+ return rc;
}
static int handle_skey(struct kvm_vcpu *vcpu)
{
- __skey_check_enable(vcpu);
+ int rc = __skey_check_enable(vcpu);
+ if (rc)
+ return rc;
vcpu->stat.instruction_storage_key++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- vcpu->arch.sie_block->gpsw.addr =
- __rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+ kvm_s390_rewind_psw(vcpu, 4);
VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
return 0;
}
static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
{
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
-
vcpu->stat.instruction_ipte_interlock++;
- if (psw_bits(*psw).p)
+ 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));
- psw->addr = __rewind_psw(*psw, 4);
+ kvm_s390_rewind_psw(vcpu, 4);
VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
return 0;
}
@@ -206,7 +211,7 @@ static int handle_test_block(struct kvm_vcpu *vcpu)
kvm_s390_get_regs_rre(vcpu, NULL, &reg2);
addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
addr = kvm_s390_logical_to_effective(vcpu, addr);
- if (kvm_s390_check_low_addr_protection(vcpu, addr))
+ if (kvm_s390_check_low_addr_prot_real(vcpu, addr))
return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
addr = kvm_s390_real_to_abs(vcpu, addr);
@@ -228,18 +233,20 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
struct kvm_s390_interrupt_info *inti;
unsigned long len;
u32 tpi_data[3];
- int cc, rc;
+ int rc;
u64 addr;
+ ar_t ar;
- rc = 0;
- addr = kvm_s390_get_base_disp_s(vcpu);
+ addr = kvm_s390_get_base_disp_s(vcpu, &ar);
if (addr & 3)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- cc = 0;
+
inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0);
- if (!inti)
- goto no_interrupt;
- cc = 1;
+ if (!inti) {
+ kvm_s390_set_psw_cc(vcpu, 0);
+ return 0;
+ }
+
tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr;
tpi_data[1] = inti->io.io_int_parm;
tpi_data[2] = inti->io.io_int_word;
@@ -249,40 +256,51 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
* provided area.
*/
len = sizeof(tpi_data) - 4;
- rc = write_guest(vcpu, addr, &tpi_data, len);
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
+ rc = write_guest(vcpu, addr, ar, &tpi_data, len);
+ if (rc) {
+ rc = kvm_s390_inject_prog_cond(vcpu, rc);
+ goto reinject_interrupt;
+ }
} else {
/*
* Store the three-word I/O interruption code into
* the appropriate lowcore area.
*/
len = sizeof(tpi_data);
- if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len))
+ if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) {
+ /* failed writes to the low core are not recoverable */
rc = -EFAULT;
+ goto reinject_interrupt;
+ }
}
+
+ /* irq was successfully handed to the guest */
+ kfree(inti);
+ kvm_s390_set_psw_cc(vcpu, 1);
+ return 0;
+reinject_interrupt:
/*
* If we encounter a problem storing the interruption code, the
* instruction is suppressed from the guest's view: reinject the
* interrupt.
*/
- if (!rc)
+ if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) {
kfree(inti);
- else
- kvm_s390_reinject_io_int(vcpu->kvm, inti);
-no_interrupt:
- /* Set condition code and we're done. */
- if (!rc)
- kvm_s390_set_psw_cc(vcpu, cc);
+ rc = -EFAULT;
+ }
+ /* don't set the cc, a pgm irq was injected or we drop to user space */
return rc ? -EFAULT : 0;
}
static int handle_tsch(struct kvm_vcpu *vcpu)
{
- struct kvm_s390_interrupt_info *inti;
+ struct kvm_s390_interrupt_info *inti = NULL;
+ const u64 isc_mask = 0xffUL << 24; /* all iscs set */
- inti = kvm_s390_get_io_int(vcpu->kvm, 0,
- vcpu->run->s.regs.gprs[1]);
+ /* a valid schid has at least one bit set */
+ if (vcpu->run->s.regs.gprs[1])
+ inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask,
+ vcpu->run->s.regs.gprs[1]);
/*
* Prepare exit to userspace.
@@ -336,29 +354,27 @@ static int handle_io_inst(struct kvm_vcpu *vcpu)
static int handle_stfl(struct kvm_vcpu *vcpu)
{
int rc;
+ unsigned int fac;
vcpu->stat.instruction_stfl++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+ /*
+ * 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),
- vfacilities, 4);
+ &fac, sizeof(fac));
if (rc)
return rc;
- VCPU_EVENT(vcpu, 5, "store facility list value %x",
- *(unsigned int *) vfacilities);
- trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities);
+ VCPU_EVENT(vcpu, 5, "store facility list value %x", fac);
+ trace_kvm_s390_handle_stfl(vcpu, fac);
return 0;
}
-static void handle_new_psw(struct kvm_vcpu *vcpu)
-{
- /* Check whether the new psw is enabled for machine checks. */
- if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK)
- kvm_s390_deliver_pending_machine_checks(vcpu);
-}
-
#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA)
#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL
#define PSW_ADDR_24 0x0000000000ffffffUL
@@ -387,15 +403,16 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
psw_compat_t new_psw;
u64 addr;
int rc;
+ ar_t ar;
if (gpsw->mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- addr = kvm_s390_get_base_disp_s(vcpu);
+ addr = kvm_s390_get_base_disp_s(vcpu, &ar);
if (addr & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw));
+ rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
if (!(new_psw.mask & PSW32_MASK_BASE))
@@ -405,7 +422,6 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
gpsw->addr = new_psw.addr & ~PSW32_ADDR_AMODE;
if (!is_valid_psw(gpsw))
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- handle_new_psw(vcpu);
return 0;
}
@@ -414,20 +430,20 @@ static int handle_lpswe(struct kvm_vcpu *vcpu)
psw_t new_psw;
u64 addr;
int rc;
+ ar_t ar;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- addr = kvm_s390_get_base_disp_s(vcpu);
+ addr = kvm_s390_get_base_disp_s(vcpu, &ar);
if (addr & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw));
+ rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
vcpu->arch.sie_block->gpsw = new_psw;
if (!is_valid_psw(&vcpu->arch.sie_block->gpsw))
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- handle_new_psw(vcpu);
return 0;
}
@@ -436,18 +452,19 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
u64 stidp_data = vcpu->arch.stidp_data;
u64 operand2;
int rc;
+ ar_t ar;
vcpu->stat.instruction_stidp++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- operand2 = kvm_s390_get_base_disp_s(vcpu);
+ operand2 = kvm_s390_get_base_disp_s(vcpu, &ar);
if (operand2 & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- rc = write_guest(vcpu, operand2, &stidp_data, sizeof(stidp_data));
+ rc = write_guest(vcpu, operand2, ar, &stidp_data, sizeof(stidp_data));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
@@ -470,6 +487,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
for (n = mem->count - 1; n > 0 ; n--)
memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
+ memset(&mem->vm[0], 0, sizeof(mem->vm[0]));
mem->vm[0].cpus_total = cpus;
mem->vm[0].cpus_configured = cpus;
mem->vm[0].cpus_standby = 0;
@@ -481,6 +499,17 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
ASCEBC(mem->vm[0].cpi, 16);
}
+static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar,
+ u8 fc, u8 sel1, u16 sel2)
+{
+ vcpu->run->exit_reason = KVM_EXIT_S390_STSI;
+ vcpu->run->s390_stsi.addr = addr;
+ vcpu->run->s390_stsi.ar = ar;
+ vcpu->run->s390_stsi.fc = fc;
+ vcpu->run->s390_stsi.sel1 = sel1;
+ vcpu->run->s390_stsi.sel2 = sel2;
+}
+
static int handle_stsi(struct kvm_vcpu *vcpu)
{
int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
@@ -489,6 +518,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
unsigned long mem = 0;
u64 operand2;
int rc = 0;
+ ar_t ar;
vcpu->stat.instruction_stsi++;
VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
@@ -511,7 +541,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
return 0;
}
- operand2 = kvm_s390_get_base_disp_s(vcpu);
+ operand2 = kvm_s390_get_base_disp_s(vcpu, &ar);
if (operand2 & 0xfff)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -535,16 +565,20 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
break;
}
- rc = write_guest(vcpu, operand2, (void *)mem, PAGE_SIZE);
+ rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE);
if (rc) {
rc = kvm_s390_inject_prog_cond(vcpu, rc);
goto out;
}
+ if (vcpu->kvm->arch.user_stsi) {
+ insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2);
+ rc = -EREMOTE;
+ }
trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
free_page(mem);
kvm_s390_set_psw_cc(vcpu, 0);
vcpu->run->s.regs.gprs[0] = 0;
- return 0;
+ return rc;
out_no_data:
kvm_s390_set_psw_cc(vcpu, 3);
out:
@@ -655,10 +689,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
- if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
- if (kvm_s390_check_low_addr_protection(vcpu, start))
- return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
- }
+ start = kvm_s390_logical_to_effective(vcpu, start);
switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
case 0x00000000:
@@ -674,6 +705,12 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
default:
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
}
+
+ if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
+ if (kvm_s390_check_low_addr_prot_real(vcpu, start))
+ return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+ }
+
while (start < end) {
unsigned long useraddr, abs_addr;
@@ -692,7 +729,10 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
}
if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK) {
- __skey_check_enable(vcpu);
+ int rc = __skey_check_enable(vcpu);
+
+ if (rc)
+ return rc;
if (set_guest_storage_key(current->mm, useraddr,
vcpu->run->s.regs.gprs[reg1] & PFMF_KEY,
vcpu->run->s.regs.gprs[reg1] & PFMF_NQ))
@@ -727,8 +767,7 @@ static int handle_essa(struct kvm_vcpu *vcpu)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
/* Rewind PSW to repeat the ESSA instruction */
- vcpu->arch.sie_block->gpsw.addr =
- __rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+ kvm_s390_rewind_psw(vcpu, 4);
vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */
cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
down_read(&gmap->mm->mmap_sem);
@@ -738,7 +777,7 @@ static int handle_essa(struct kvm_vcpu *vcpu)
/* invalid entry */
break;
/* try to free backing */
- __gmap_zap(cbrle, gmap);
+ __gmap_zap(gmap, cbrle);
}
up_read(&gmap->mm->mmap_sem);
if (i < entries)
@@ -771,16 +810,17 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
- u32 val = 0;
- int reg, rc;
+ int reg, rc, nr_regs;
+ u32 ctl_array[16];
u64 ga;
+ ar_t ar;
vcpu->stat.instruction_lctl++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- ga = kvm_s390_get_base_disp_rs(vcpu);
+ ga = kvm_s390_get_base_disp_rs(vcpu, &ar);
if (ga & 3)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -788,19 +828,20 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga);
+ nr_regs = ((reg3 - reg1) & 0xf) + 1;
+ rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32));
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
reg = reg1;
+ nr_regs = 0;
do {
- rc = read_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul;
- vcpu->arch.sie_block->gcr[reg] |= val;
- ga += 4;
+ vcpu->arch.sie_block->gcr[reg] |= ctl_array[nr_regs++];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return 0;
}
@@ -808,16 +849,17 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+ int reg, rc, nr_regs;
+ u32 ctl_array[16];
u64 ga;
- u32 val;
- int reg, rc;
+ ar_t ar;
vcpu->stat.instruction_stctl++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- ga = kvm_s390_get_base_disp_rs(vcpu);
+ ga = kvm_s390_get_base_disp_rs(vcpu, &ar);
if (ga & 3)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -826,53 +868,52 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga);
reg = reg1;
+ nr_regs = 0;
do {
- val = vcpu->arch.sie_block->gcr[reg] & 0x00000000fffffffful;
- rc = write_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- ga += 4;
+ ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
- return 0;
+ rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32));
+ return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
}
static int handle_lctlg(struct kvm_vcpu *vcpu)
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
- u64 ga, val;
- int reg, rc;
+ int reg, rc, nr_regs;
+ u64 ctl_array[16];
+ u64 ga;
+ ar_t ar;
vcpu->stat.instruction_lctlg++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- ga = kvm_s390_get_base_disp_rsy(vcpu);
+ ga = kvm_s390_get_base_disp_rsy(vcpu, &ar);
if (ga & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- reg = reg1;
-
VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga);
+ nr_regs = ((reg3 - reg1) & 0xf) + 1;
+ rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64));
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
+ reg = reg1;
+ nr_regs = 0;
do {
- rc = read_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- vcpu->arch.sie_block->gcr[reg] = val;
- ga += 8;
+ vcpu->arch.sie_block->gcr[reg] = ctl_array[nr_regs++];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return 0;
}
@@ -880,36 +921,34 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
- u64 ga, val;
- int reg, rc;
+ int reg, rc, nr_regs;
+ u64 ctl_array[16];
+ u64 ga;
+ ar_t ar;
vcpu->stat.instruction_stctg++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- ga = kvm_s390_get_base_disp_rsy(vcpu);
+ ga = kvm_s390_get_base_disp_rsy(vcpu, &ar);
if (ga & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- reg = reg1;
-
VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga);
+ reg = reg1;
+ nr_regs = 0;
do {
- val = vcpu->arch.sie_block->gcr[reg];
- rc = write_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- ga += 8;
+ ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
- return 0;
+ rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64));
+ return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
}
static const intercept_handler_t eb_handlers[256] = {
@@ -933,13 +972,14 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
unsigned long hva, gpa;
int ret = 0, cc = 0;
bool writable;
+ ar_t ar;
vcpu->stat.instruction_tprot++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- kvm_s390_get_base_disp_sse(vcpu, &address1, &address2);
+ kvm_s390_get_base_disp_sse(vcpu, &address1, &address2, &ar, NULL);
/* we only handle the Linux memory detection case:
* access key == 0
@@ -948,11 +988,11 @@ 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, &gpa, 1);
+ ret = guest_translate_address(vcpu, address1, ar, &gpa, 1);
if (ret == PGM_PROTECTION) {
/* Write protected? Try again with read-only... */
cc = 1;
- ret = guest_translate_address(vcpu, address1, &gpa, 0);
+ ret = guest_translate_address(vcpu, address1, ar, &gpa, 0);
}
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 43079a48cc98..72e58bd2bee7 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -20,83 +20,76 @@
#include "kvm-s390.h"
#include "trace.h"
-static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
+static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
u64 *reg)
{
struct kvm_s390_local_interrupt *li;
- struct kvm_vcpu *dst_vcpu = NULL;
int cpuflags;
int rc;
+ int ext_call_pending;
- 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;
li = &dst_vcpu->arch.local_int;
cpuflags = atomic_read(li->cpuflags);
- if (!(cpuflags & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED)))
+ ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu);
+ if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending)
rc = SIGP_CC_ORDER_CODE_ACCEPTED;
else {
*reg &= 0xffffffff00000000UL;
- if (cpuflags & CPUSTAT_ECALL_PEND)
+ if (ext_call_pending)
*reg |= SIGP_STATUS_EXT_CALL_PENDING;
if (cpuflags & CPUSTAT_STOPPED)
*reg |= SIGP_STATUS_STOPPED;
rc = SIGP_CC_STATUS_STORED;
}
- VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc);
+ VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", dst_vcpu->vcpu_id,
+ rc);
return rc;
}
-static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
+static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu)
{
- struct kvm_s390_interrupt s390int = {
+ struct kvm_s390_irq irq = {
.type = KVM_S390_INT_EMERGENCY,
- .parm = vcpu->vcpu_id,
+ .u.emerg.code = vcpu->vcpu_id,
};
- struct kvm_vcpu *dst_vcpu = NULL;
int rc = 0;
- if (cpu_addr < KVM_MAX_VCPUS)
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
- if (!dst_vcpu)
- return SIGP_CC_NOT_OPERATIONAL;
-
- rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int);
+ rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
if (!rc)
- VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
+ VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x",
+ dst_vcpu->vcpu_id);
return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED;
}
-static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr,
+static int __sigp_emergency(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu)
+{
+ return __inject_sigp_emergency(vcpu, dst_vcpu);
+}
+
+static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu,
u16 asn, u64 *reg)
{
- struct kvm_vcpu *dst_vcpu = NULL;
const u64 psw_int_mask = PSW_MASK_IO | PSW_MASK_EXT;
u16 p_asn, s_asn;
psw_t *psw;
u32 flags;
- if (cpu_addr < KVM_MAX_VCPUS)
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
- if (!dst_vcpu)
- return SIGP_CC_NOT_OPERATIONAL;
flags = atomic_read(&dst_vcpu->arch.sie_block->cpuflags);
psw = &dst_vcpu->arch.sie_block->gpsw;
p_asn = dst_vcpu->arch.sie_block->gcr[4] & 0xffff; /* Primary ASN */
s_asn = dst_vcpu->arch.sie_block->gcr[3] & 0xffff; /* Secondary ASN */
- /* Deliver the emergency signal? */
+ /* Inject the emergency signal? */
if (!(flags & CPUSTAT_STOPPED)
|| (psw->mask & psw_int_mask) != psw_int_mask
|| ((flags & CPUSTAT_WAIT) && psw->addr != 0)
|| (!(flags & CPUSTAT_WAIT) && (asn == p_asn || asn == s_asn))) {
- return __sigp_emergency(vcpu, cpu_addr);
+ return __inject_sigp_emergency(vcpu, dst_vcpu);
} else {
*reg &= 0xffffffff00000000UL;
*reg |= SIGP_STATUS_INCORRECT_STATE;
@@ -104,81 +97,60 @@ static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr,
}
}
-static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
+static int __sigp_external_call(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu, u64 *reg)
{
- struct kvm_s390_interrupt s390int = {
+ struct kvm_s390_irq irq = {
.type = KVM_S390_INT_EXTERNAL_CALL,
- .parm = vcpu->vcpu_id,
+ .u.extcall.code = vcpu->vcpu_id,
};
- struct kvm_vcpu *dst_vcpu = NULL;
int rc;
- if (cpu_addr < KVM_MAX_VCPUS)
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
- if (!dst_vcpu)
- return SIGP_CC_NOT_OPERATIONAL;
-
- rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int);
- if (!rc)
- VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr);
+ rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
+ if (rc == -EBUSY) {
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STATUS_EXT_CALL_PENDING;
+ return SIGP_CC_STATUS_STORED;
+ } else if (rc == 0) {
+ VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x",
+ dst_vcpu->vcpu_id);
+ }
return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED;
}
-static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
+static int __sigp_stop(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu)
{
- struct kvm_s390_interrupt_info *inti;
- int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
-
- inti = kzalloc(sizeof(*inti), GFP_ATOMIC);
- if (!inti)
- return -ENOMEM;
- inti->type = KVM_S390_SIGP_STOP;
-
- spin_lock_bh(&li->lock);
- if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
- kfree(inti);
- if ((action & ACTION_STORE_ON_STOP) != 0)
- rc = -ESHUTDOWN;
- goto out;
- }
- list_add_tail(&inti->list, &li->list);
- atomic_set(&li->active, 1);
- atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
- li->action_bits |= action;
- if (waitqueue_active(li->wq))
- wake_up_interruptible(li->wq);
-out:
- spin_unlock_bh(&li->lock);
+ struct kvm_s390_irq irq = {
+ .type = KVM_S390_SIGP_STOP,
+ };
+ int rc;
+
+ rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
+ if (rc == -EBUSY)
+ rc = SIGP_CC_BUSY;
+ else if (rc == 0)
+ VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x",
+ dst_vcpu->vcpu_id);
return rc;
}
-static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
+static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu, u64 *reg)
{
- struct kvm_s390_local_interrupt *li;
- struct kvm_vcpu *dst_vcpu = NULL;
+ struct kvm_s390_irq irq = {
+ .type = KVM_S390_SIGP_STOP,
+ .u.stop.flags = KVM_S390_STOP_FLAG_STORE_STATUS,
+ };
int rc;
- 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;
- li = &dst_vcpu->arch.local_int;
-
- rc = __inject_sigp_stop(li, action);
-
- VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
-
- if ((action & ACTION_STORE_ON_STOP) != 0 && rc == -ESHUTDOWN) {
- /* If the CPU has already been stopped, we still have
- * to save the status when doing stop-and-store. This
- * has to be done after unlocking all spinlocks. */
- rc = kvm_s390_store_status_unloaded(dst_vcpu,
- KVM_S390_STORE_STATUS_NOADDR);
- }
+ rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
+ if (rc == -EBUSY)
+ rc = SIGP_CC_BUSY;
+ else if (rc == 0)
+ VCPU_EVENT(vcpu, 4, "sent sigp stop and store status to cpu %x",
+ dst_vcpu->vcpu_id);
return rc;
}
@@ -208,76 +180,47 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
return rc;
}
-static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
- u64 *reg)
+static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
+ u32 address, u64 *reg)
{
- struct kvm_s390_local_interrupt *li;
- struct kvm_vcpu *dst_vcpu = NULL;
- struct kvm_s390_interrupt_info *inti;
+ struct kvm_s390_irq irq = {
+ .type = KVM_S390_SIGP_SET_PREFIX,
+ .u.prefix.address = address & 0x7fffe000u,
+ };
int rc;
- if (cpu_addr < KVM_MAX_VCPUS)
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
- if (!dst_vcpu)
- return SIGP_CC_NOT_OPERATIONAL;
- li = &dst_vcpu->arch.local_int;
-
/*
* Make sure the new value is valid memory. We only need to check the
* first page, since address is 8k aligned and memory pieces are always
* at least 1MB aligned and have at least a size of 1MB.
*/
- address &= 0x7fffe000u;
- if (kvm_is_error_gpa(vcpu->kvm, address)) {
+ if (kvm_is_error_gpa(vcpu->kvm, irq.u.prefix.address)) {
*reg &= 0xffffffff00000000UL;
*reg |= SIGP_STATUS_INVALID_PARAMETER;
return SIGP_CC_STATUS_STORED;
}
- inti = kzalloc(sizeof(*inti), GFP_KERNEL);
- if (!inti)
- return SIGP_CC_BUSY;
-
- spin_lock_bh(&li->lock);
- /* cpu must be in stopped state */
- if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
+ rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
+ if (rc == -EBUSY) {
*reg &= 0xffffffff00000000UL;
*reg |= SIGP_STATUS_INCORRECT_STATE;
- rc = SIGP_CC_STATUS_STORED;
- kfree(inti);
- goto out_li;
+ return SIGP_CC_STATUS_STORED;
+ } else if (rc == 0) {
+ VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x",
+ dst_vcpu->vcpu_id, irq.u.prefix.address);
}
- inti->type = KVM_S390_SIGP_SET_PREFIX;
- inti->prefix.address = address;
-
- list_add_tail(&inti->list, &li->list);
- atomic_set(&li->active, 1);
- if (waitqueue_active(li->wq))
- wake_up_interruptible(li->wq);
- rc = SIGP_CC_ORDER_CODE_ACCEPTED;
-
- VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address);
-out_li:
- spin_unlock_bh(&li->lock);
return rc;
}
-static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, u16 cpu_id,
- u32 addr, u64 *reg)
+static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu,
+ u32 addr, u64 *reg)
{
- struct kvm_vcpu *dst_vcpu = NULL;
int flags;
int rc;
- if (cpu_id < KVM_MAX_VCPUS)
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_id);
- if (!dst_vcpu)
- return SIGP_CC_NOT_OPERATIONAL;
-
- spin_lock_bh(&dst_vcpu->arch.local_int.lock);
flags = atomic_read(dst_vcpu->arch.local_int.cpuflags);
- spin_unlock_bh(&dst_vcpu->arch.local_int.lock);
if (!(flags & CPUSTAT_STOPPED)) {
*reg &= 0xffffffff00000000UL;
*reg |= SIGP_STATUS_INCORRECT_STATE;
@@ -294,19 +237,12 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, u16 cpu_id,
return rc;
}
-static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
- u64 *reg)
+static int __sigp_sense_running(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu, u64 *reg)
{
struct kvm_s390_local_interrupt *li;
- struct kvm_vcpu *dst_vcpu = NULL;
int rc;
- 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;
li = &dst_vcpu->arch.local_int;
if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
/* running */
@@ -318,118 +254,205 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
rc = SIGP_CC_STATUS_STORED;
}
- VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
- rc);
+ VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x",
+ dst_vcpu->vcpu_id, rc);
return rc;
}
-/* Test whether the destination CPU is available and not busy */
-static int sigp_check_callable(struct kvm_vcpu *vcpu, u16 cpu_addr)
+static int __prepare_sigp_re_start(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu, u8 order_code)
{
- struct kvm_s390_local_interrupt *li;
- int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
- struct kvm_vcpu *dst_vcpu = NULL;
-
- if (cpu_addr >= KVM_MAX_VCPUS)
- return SIGP_CC_NOT_OPERATIONAL;
+ struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int;
+ /* handle (RE)START in user space */
+ int rc = -EOPNOTSUPP;
- dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
- if (!dst_vcpu)
- return SIGP_CC_NOT_OPERATIONAL;
- li = &dst_vcpu->arch.local_int;
- spin_lock_bh(&li->lock);
- if (li->action_bits & ACTION_STOP_ON_STOP)
+ /* make sure we don't race with STOP irq injection */
+ spin_lock(&li->lock);
+ if (kvm_s390_is_stop_irq_pending(dst_vcpu))
rc = SIGP_CC_BUSY;
- spin_unlock_bh(&li->lock);
+ spin_unlock(&li->lock);
return rc;
}
-int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
+static int __prepare_sigp_cpu_reset(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu, u8 order_code)
{
- int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
- int r3 = vcpu->arch.sie_block->ipa & 0x000f;
- u32 parameter;
- u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
- u8 order_code;
- int rc;
+ /* handle (INITIAL) CPU RESET in user space */
+ return -EOPNOTSUPP;
+}
- /* sigp in userspace can exit */
- if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
- return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+static int __prepare_sigp_unknown(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu *dst_vcpu)
+{
+ /* handle unknown orders in user space */
+ return -EOPNOTSUPP;
+}
- order_code = kvm_s390_get_base_disp_rs(vcpu);
+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;
- if (r1 % 2)
- parameter = vcpu->run->s.regs.gprs[r1];
- else
- parameter = vcpu->run->s.regs.gprs[r1 + 1];
+ 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;
- trace_kvm_s390_handle_sigp(vcpu, order_code, cpu_addr, parameter);
switch (order_code) {
case SIGP_SENSE:
vcpu->stat.instruction_sigp_sense++;
- rc = __sigp_sense(vcpu, cpu_addr,
- &vcpu->run->s.regs.gprs[r1]);
+ rc = __sigp_sense(vcpu, dst_vcpu, status_reg);
break;
case SIGP_EXTERNAL_CALL:
vcpu->stat.instruction_sigp_external_call++;
- rc = __sigp_external_call(vcpu, cpu_addr);
+ rc = __sigp_external_call(vcpu, dst_vcpu, status_reg);
break;
case SIGP_EMERGENCY_SIGNAL:
vcpu->stat.instruction_sigp_emergency++;
- rc = __sigp_emergency(vcpu, cpu_addr);
+ rc = __sigp_emergency(vcpu, dst_vcpu);
break;
case SIGP_STOP:
vcpu->stat.instruction_sigp_stop++;
- rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP);
+ rc = __sigp_stop(vcpu, dst_vcpu);
break;
case SIGP_STOP_AND_STORE_STATUS:
- vcpu->stat.instruction_sigp_stop++;
- rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP |
- ACTION_STOP_ON_STOP);
+ vcpu->stat.instruction_sigp_stop_store_status++;
+ rc = __sigp_stop_and_store_status(vcpu, dst_vcpu, status_reg);
break;
case SIGP_STORE_STATUS_AT_ADDRESS:
- rc = __sigp_store_status_at_addr(vcpu, cpu_addr, parameter,
- &vcpu->run->s.regs.gprs[r1]);
- break;
- case SIGP_SET_ARCHITECTURE:
- vcpu->stat.instruction_sigp_arch++;
- rc = __sigp_set_arch(vcpu, parameter);
+ vcpu->stat.instruction_sigp_store_status++;
+ rc = __sigp_store_status_at_addr(vcpu, dst_vcpu, parameter,
+ status_reg);
break;
case SIGP_SET_PREFIX:
vcpu->stat.instruction_sigp_prefix++;
- rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
- &vcpu->run->s.regs.gprs[r1]);
+ rc = __sigp_set_prefix(vcpu, dst_vcpu, parameter, status_reg);
break;
case SIGP_COND_EMERGENCY_SIGNAL:
- rc = __sigp_conditional_emergency(vcpu, cpu_addr, parameter,
- &vcpu->run->s.regs.gprs[r1]);
+ vcpu->stat.instruction_sigp_cond_emergency++;
+ rc = __sigp_conditional_emergency(vcpu, dst_vcpu, parameter,
+ status_reg);
break;
case SIGP_SENSE_RUNNING:
vcpu->stat.instruction_sigp_sense_running++;
- rc = __sigp_sense_running(vcpu, cpu_addr,
- &vcpu->run->s.regs.gprs[r1]);
+ rc = __sigp_sense_running(vcpu, dst_vcpu, status_reg);
break;
case SIGP_START:
- rc = sigp_check_callable(vcpu, cpu_addr);
- if (rc == SIGP_CC_ORDER_CODE_ACCEPTED)
- rc = -EOPNOTSUPP; /* Handle START in user space */
+ vcpu->stat.instruction_sigp_start++;
+ rc = __prepare_sigp_re_start(vcpu, dst_vcpu, order_code);
break;
case SIGP_RESTART:
vcpu->stat.instruction_sigp_restart++;
- rc = sigp_check_callable(vcpu, cpu_addr);
- if (rc == SIGP_CC_ORDER_CODE_ACCEPTED) {
- VCPU_EVENT(vcpu, 4,
- "sigp restart %x to handle userspace",
- cpu_addr);
- /* user space must know about restart */
- rc = -EOPNOTSUPP;
- }
+ rc = __prepare_sigp_re_start(vcpu, dst_vcpu, order_code);
+ break;
+ case SIGP_INITIAL_CPU_RESET:
+ vcpu->stat.instruction_sigp_init_cpu_reset++;
+ rc = __prepare_sigp_cpu_reset(vcpu, dst_vcpu, order_code);
+ break;
+ case SIGP_CPU_RESET:
+ vcpu->stat.instruction_sigp_cpu_reset++;
+ rc = __prepare_sigp_cpu_reset(vcpu, dst_vcpu, order_code);
+ break;
+ default:
+ vcpu->stat.instruction_sigp_unknown++;
+ rc = __prepare_sigp_unknown(vcpu, dst_vcpu);
+ }
+
+ if (rc == -EOPNOTSUPP)
+ VCPU_EVENT(vcpu, 4,
+ "sigp order %u -> cpu %x: handled in user space",
+ order_code, dst_vcpu->vcpu_id);
+
+ return rc;
+}
+
+static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code)
+{
+ if (!vcpu->kvm->arch.user_sigp)
+ return 0;
+
+ switch (order_code) {
+ case SIGP_SENSE:
+ case SIGP_EXTERNAL_CALL:
+ case SIGP_EMERGENCY_SIGNAL:
+ case SIGP_COND_EMERGENCY_SIGNAL:
+ case SIGP_SENSE_RUNNING:
+ return 0;
+ /* update counters as we're directly dropping to user space */
+ case SIGP_STOP:
+ vcpu->stat.instruction_sigp_stop++;
+ break;
+ case SIGP_STOP_AND_STORE_STATUS:
+ vcpu->stat.instruction_sigp_stop_store_status++;
+ break;
+ case SIGP_STORE_STATUS_AT_ADDRESS:
+ vcpu->stat.instruction_sigp_store_status++;
+ break;
+ case SIGP_STORE_ADDITIONAL_STATUS:
+ vcpu->stat.instruction_sigp_store_adtl_status++;
+ break;
+ case SIGP_SET_PREFIX:
+ vcpu->stat.instruction_sigp_prefix++;
+ break;
+ case SIGP_START:
+ vcpu->stat.instruction_sigp_start++;
+ break;
+ case SIGP_RESTART:
+ vcpu->stat.instruction_sigp_restart++;
+ break;
+ case SIGP_INITIAL_CPU_RESET:
+ vcpu->stat.instruction_sigp_init_cpu_reset++;
+ break;
+ case SIGP_CPU_RESET:
+ vcpu->stat.instruction_sigp_cpu_reset++;
break;
default:
+ vcpu->stat.instruction_sigp_unknown++;
+ }
+
+ VCPU_EVENT(vcpu, 4, "sigp order %u: completely handled in user space",
+ order_code);
+
+ return 1;
+}
+
+int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
+{
+ int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+ int r3 = vcpu->arch.sie_block->ipa & 0x000f;
+ u32 parameter;
+ u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
+ u8 order_code;
+ int rc;
+
+ /* sigp in userspace can exit */
+ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+ return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+ order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
+ if (handle_sigp_order_in_user_space(vcpu, order_code))
return -EOPNOTSUPP;
+
+ if (r1 % 2)
+ parameter = vcpu->run->s.regs.gprs[r1];
+ else
+ parameter = vcpu->run->s.regs.gprs[r1 + 1];
+
+ trace_kvm_s390_handle_sigp(vcpu, order_code, cpu_addr, parameter);
+ switch (order_code) {
+ case SIGP_SET_ARCHITECTURE:
+ vcpu->stat.instruction_sigp_arch++;
+ rc = __sigp_set_arch(vcpu, parameter);
+ break;
+ default:
+ rc = handle_sigp_dst(vcpu, order_code, cpu_addr,
+ parameter,
+ &vcpu->run->s.regs.gprs[r1]);
}
if (rc < 0)
@@ -453,7 +476,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
int r3 = vcpu->arch.sie_block->ipa & 0x000f;
u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
struct kvm_vcpu *dest_vcpu;
- u8 order_code = kvm_s390_get_base_disp_rs(vcpu);
+ u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
@@ -461,12 +484,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
BUG_ON(dest_vcpu == NULL);
- spin_lock_bh(&dest_vcpu->arch.local_int.lock);
- if (waitqueue_active(&dest_vcpu->wq))
- wake_up_interruptible(&dest_vcpu->wq);
- dest_vcpu->preempted = true;
- spin_unlock_bh(&dest_vcpu->arch.local_int.lock);
-
+ kvm_s390_vcpu_wakeup(dest_vcpu);
kvm_s390_set_psw_cc(vcpu, SIGP_CC_ORDER_CODE_ACCEPTED);
return 0;
}
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index 647e9d6a4818..3208d33a48cb 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -10,6 +10,13 @@
#define TRACE_INCLUDE_FILE trace-s390
/*
+ * The TRACE_SYSTEM_VAR defaults to TRACE_SYSTEM, but must be a
+ * legitimate C variable. It is not exported to user space.
+ */
+#undef TRACE_SYSTEM_VAR
+#define TRACE_SYSTEM_VAR kvm_s390
+
+/*
* Trace point for the creation of the kvm instance.
*/
TRACE_EVENT(kvm_s390_create_vm,
@@ -209,19 +216,21 @@ TRACE_EVENT(kvm_s390_request_resets,
* Trace point for a vcpu's stop requests.
*/
TRACE_EVENT(kvm_s390_stop_request,
- TP_PROTO(unsigned int action_bits),
- TP_ARGS(action_bits),
+ TP_PROTO(unsigned char stop_irq, unsigned char flags),
+ TP_ARGS(stop_irq, flags),
TP_STRUCT__entry(
- __field(unsigned int, action_bits)
+ __field(unsigned char, stop_irq)
+ __field(unsigned char, flags)
),
TP_fast_assign(
- __entry->action_bits = action_bits;
+ __entry->stop_irq = stop_irq;
+ __entry->flags = flags;
),
- TP_printk("stop request, action_bits = %08x",
- __entry->action_bits)
+ TP_printk("stop request, stop irq = %u, flags = %08x",
+ __entry->stop_irq, __entry->flags)
);
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-02 19:28:35 +0300