summaryrefslogtreecommitdiff
path: root/arch/s390
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-03-16 09:55:35 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-03-16 09:55:35 -0700
commit10dc3747661bea9215417b659449bb7b8ed3df2c (patch)
treed943974b4941203a7db2fabe4896852cf0f16bc4 /arch/s390
parent047486d8e7c2a7e8d75b068b69cb67b47364f5d4 (diff)
parentf958ee745f70b60d0e41927cab2c073104bc70c2 (diff)
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini: "One of the largest releases for KVM... Hardly any generic changes, but lots of architecture-specific updates. ARM: - VHE support so that we can run the kernel at EL2 on ARMv8.1 systems - PMU support for guests - 32bit world switch rewritten in C - various optimizations to the vgic save/restore code. PPC: - enabled KVM-VFIO integration ("VFIO device") - optimizations to speed up IPIs between vcpus - in-kernel handling of IOMMU hypercalls - support for dynamic DMA windows (DDW). s390: - provide the floating point registers via sync regs; - separated instruction vs. data accesses - dirty log improvements for huge guests - bugfixes and documentation improvements. x86: - Hyper-V VMBus hypercall userspace exit - alternative implementation of lowest-priority interrupts using vector hashing (for better VT-d posted interrupt support) - fixed guest debugging with nested virtualizations - improved interrupt tracking in the in-kernel IOAPIC - generic infrastructure for tracking writes to guest memory - currently its only use is to speedup the legacy shadow paging (pre-EPT) case, but in the future it will be used for virtual GPUs as well - much cleanup (LAPIC, kvmclock, MMU, PIT), including ubsan fixes" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (217 commits) KVM: x86: remove eager_fpu field of struct kvm_vcpu_arch KVM: x86: disable MPX if host did not enable MPX XSAVE features arm64: KVM: vgic-v3: Only wipe LRs on vcpu exit arm64: KVM: vgic-v3: Reset LRs at boot time arm64: KVM: vgic-v3: Do not save an LR known to be empty arm64: KVM: vgic-v3: Save maintenance interrupt state only if required arm64: KVM: vgic-v3: Avoid accessing ICH registers KVM: arm/arm64: vgic-v2: Make GICD_SGIR quicker to hit KVM: arm/arm64: vgic-v2: Only wipe LRs on vcpu exit KVM: arm/arm64: vgic-v2: Reset LRs at boot time KVM: arm/arm64: vgic-v2: Do not save an LR known to be empty KVM: arm/arm64: vgic-v2: Move GICH_ELRSR saving to its own function KVM: arm/arm64: vgic-v2: Save maintenance interrupt state only if required KVM: arm/arm64: vgic-v2: Avoid accessing GICH registers KVM: s390: allocate only one DMA page per VM KVM: s390: enable STFLE interpretation only if enabled for the guest KVM: s390: wake up when the VCPU cpu timer expires KVM: s390: step the VCPU timer while in enabled wait KVM: s390: protect VCPU cpu timer with a seqcount KVM: s390: step VCPU cpu timer during kvm_run ioctl ...
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/include/asm/kvm_host.h41
-rw-r--r--arch/s390/include/uapi/asm/kvm.h8
-rw-r--r--arch/s390/include/uapi/asm/sie.h1
-rw-r--r--arch/s390/kvm/gaccess.c57
-rw-r--r--arch/s390/kvm/gaccess.h38
-rw-r--r--arch/s390/kvm/intercept.c78
-rw-r--r--arch/s390/kvm/interrupt.c93
-rw-r--r--arch/s390/kvm/kvm-s390.c235
-rw-r--r--arch/s390/kvm/kvm-s390.h28
-rw-r--r--arch/s390/kvm/priv.c15
10 files changed, 402 insertions, 192 deletions
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index b0c8ad0799c7..6da41fab70fb 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -20,6 +20,7 @@
#include <linux/kvm_types.h>
#include <linux/kvm_host.h>
#include <linux/kvm.h>
+#include <linux/seqlock.h>
#include <asm/debug.h>
#include <asm/cpu.h>
#include <asm/fpu/api.h>
@@ -229,17 +230,11 @@ struct kvm_s390_itdb {
__u8 data[256];
} __packed;
-struct kvm_s390_vregs {
- __vector128 vrs[32];
- __u8 reserved200[512]; /* for future vector expansion */
-} __packed;
-
struct sie_page {
struct kvm_s390_sie_block sie_block;
__u8 reserved200[1024]; /* 0x0200 */
struct kvm_s390_itdb itdb; /* 0x0600 */
- __u8 reserved700[1280]; /* 0x0700 */
- struct kvm_s390_vregs vregs; /* 0x0c00 */
+ __u8 reserved700[2304]; /* 0x0700 */
} __packed;
struct kvm_vcpu_stat {
@@ -558,6 +553,15 @@ struct kvm_vcpu_arch {
unsigned long pfault_token;
unsigned long pfault_select;
unsigned long pfault_compare;
+ bool cputm_enabled;
+ /*
+ * The seqcount protects updates to cputm_start and sie_block.cputm,
+ * this way we can have non-blocking reads with consistent values.
+ * Only the owning VCPU thread (vcpu->cpu) is allowed to change these
+ * values and to start/stop/enable/disable cpu timer accounting.
+ */
+ seqcount_t cputm_seqcount;
+ __u64 cputm_start;
};
struct kvm_vm_stat {
@@ -596,15 +600,11 @@ struct s390_io_adapter {
#define S390_ARCH_FAC_MASK_SIZE_U64 \
(S390_ARCH_FAC_MASK_SIZE_BYTE / sizeof(u64))
-struct kvm_s390_fac {
- /* facility list requested by guest */
- __u64 list[S390_ARCH_FAC_LIST_SIZE_U64];
- /* facility mask supported by kvm & hosting machine */
- __u64 mask[S390_ARCH_FAC_LIST_SIZE_U64];
-};
-
struct kvm_s390_cpu_model {
- struct kvm_s390_fac *fac;
+ /* facility mask supported by kvm & hosting machine */
+ __u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64];
+ /* facility list requested by guest (in dma page) */
+ __u64 *fac_list;
struct cpuid cpu_id;
unsigned short ibc;
};
@@ -623,6 +623,16 @@ struct kvm_s390_crypto_cb {
__u8 reserved80[128]; /* 0x0080 */
};
+/*
+ * sie_page2 has to be allocated as DMA because fac_list and crycb need
+ * 31bit addresses in the sie control block.
+ */
+struct sie_page2 {
+ __u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */
+ struct kvm_s390_crypto_cb crycb; /* 0x0800 */
+ u8 reserved900[0x1000 - 0x900]; /* 0x0900 */
+} __packed;
+
struct kvm_arch{
void *sca;
int use_esca;
@@ -643,6 +653,7 @@ struct kvm_arch{
int ipte_lock_count;
struct mutex ipte_mutex;
spinlock_t start_stop_lock;
+ struct sie_page2 *sie_page2;
struct kvm_s390_cpu_model model;
struct kvm_s390_crypto crypto;
u64 epoch;
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index fe84bd5fe7ce..347fe5afa419 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -154,6 +154,7 @@ struct kvm_guest_debug_arch {
#define KVM_SYNC_PFAULT (1UL << 5)
#define KVM_SYNC_VRS (1UL << 6)
#define KVM_SYNC_RICCB (1UL << 7)
+#define KVM_SYNC_FPRS (1UL << 8)
/* definition of registers in kvm_run */
struct kvm_sync_regs {
__u64 prefix; /* prefix register */
@@ -168,9 +169,12 @@ struct kvm_sync_regs {
__u64 pft; /* pfault token [PFAULT] */
__u64 pfs; /* pfault select [PFAULT] */
__u64 pfc; /* pfault compare [PFAULT] */
- __u64 vrs[32][2]; /* vector registers */
+ union {
+ __u64 vrs[32][2]; /* vector registers (KVM_SYNC_VRS) */
+ __u64 fprs[16]; /* fp registers (KVM_SYNC_FPRS) */
+ };
__u8 reserved[512]; /* for future vector expansion */
- __u32 fpc; /* only valid with vector registers */
+ __u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
__u8 padding[52]; /* riccb needs to be 64byte aligned */
__u8 riccb[64]; /* runtime instrumentation controls block */
};
diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h
index ee69c0854c88..5dbaa72baa64 100644
--- a/arch/s390/include/uapi/asm/sie.h
+++ b/arch/s390/include/uapi/asm/sie.h
@@ -7,6 +7,7 @@
{ 0x9c, "DIAG (0x9c) time slice end directed" }, \
{ 0x204, "DIAG (0x204) logical-cpu utilization" }, \
{ 0x258, "DIAG (0x258) page-reference services" }, \
+ { 0x288, "DIAG (0x288) watchdog functions" }, \
{ 0x308, "DIAG (0x308) ipl functions" }, \
{ 0x500, "DIAG (0x500) KVM virtio functions" }, \
{ 0x501, "DIAG (0x501) KVM breakpoint" }
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index d30db40437dc..66938d283b77 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -373,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu)
}
static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
- int write)
+ enum gacc_mode mode)
{
union alet alet;
struct ale ale;
@@ -454,7 +454,7 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
}
}
- if (ale.fo == 1 && write)
+ if (ale.fo == 1 && mode == GACC_STORE)
return PGM_PROTECTION;
asce->val = aste.asce;
@@ -477,25 +477,28 @@ enum {
};
static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
- ar_t ar, int write)
+ ar_t ar, enum gacc_mode mode)
{
int rc;
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
+ struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
struct trans_exc_code_bits *tec_bits;
memset(pgm, 0, sizeof(*pgm));
tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
- tec_bits->fsi = write ? FSI_STORE : FSI_FETCH;
- tec_bits->as = psw_bits(*psw).as;
+ tec_bits->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH;
+ tec_bits->as = psw.as;
- if (!psw_bits(*psw).t) {
+ if (!psw.t) {
asce->val = 0;
asce->r = 1;
return 0;
}
- switch (psw_bits(vcpu->arch.sie_block->gpsw).as) {
+ if (mode == GACC_IFETCH)
+ psw.as = psw.as == PSW_AS_HOME ? PSW_AS_HOME : PSW_AS_PRIMARY;
+
+ switch (psw.as) {
case PSW_AS_PRIMARY:
asce->val = vcpu->arch.sie_block->gcr[1];
return 0;
@@ -506,7 +509,7 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
asce->val = vcpu->arch.sie_block->gcr[13];
return 0;
case PSW_AS_ACCREG:
- rc = ar_translation(vcpu, asce, ar, write);
+ rc = ar_translation(vcpu, asce, ar, mode);
switch (rc) {
case PGM_ALEN_TRANSLATION:
case PGM_ALE_SEQUENCE:
@@ -538,7 +541,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
* @gva: guest virtual address
* @gpa: points to where guest physical (absolute) address should be stored
* @asce: effective asce
- * @write: indicates if access is a write access
+ * @mode: indicates the access mode to be used
*
* Translate a guest virtual address into a guest absolute address by means
* of dynamic address translation as specified by the architecture.
@@ -554,7 +557,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
*/
static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
unsigned long *gpa, const union asce asce,
- int write)
+ enum gacc_mode mode)
{
union vaddress vaddr = {.addr = gva};
union raddress raddr = {.addr = gva};
@@ -699,7 +702,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
real_address:
raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr);
absolute_address:
- if (write && dat_protection)
+ if (mode == GACC_STORE && dat_protection)
return PGM_PROTECTION;
if (kvm_is_error_gpa(vcpu->kvm, raddr.addr))
return PGM_ADDRESSING;
@@ -728,7 +731,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
unsigned long *pages, unsigned long nr_pages,
- const union asce asce, int write)
+ const union asce asce, enum gacc_mode mode)
{
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -740,13 +743,13 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
while (nr_pages) {
ga = kvm_s390_logical_to_effective(vcpu, ga);
tec_bits->addr = ga >> PAGE_SHIFT;
- if (write && lap_enabled && is_low_address(ga)) {
+ if (mode == GACC_STORE && lap_enabled && is_low_address(ga)) {
pgm->code = PGM_PROTECTION;
return pgm->code;
}
ga &= PAGE_MASK;
if (psw_bits(*psw).t) {
- rc = guest_translate(vcpu, ga, pages, asce, write);
+ rc = guest_translate(vcpu, ga, pages, asce, mode);
if (rc < 0)
return rc;
if (rc == PGM_PROTECTION)
@@ -768,7 +771,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
}
int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
- unsigned long len, int write)
+ unsigned long len, enum gacc_mode mode)
{
psw_t *psw = &vcpu->arch.sie_block->gpsw;
unsigned long _len, nr_pages, gpa, idx;
@@ -780,7 +783,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
if (!len)
return 0;
- rc = get_vcpu_asce(vcpu, &asce, ar, write);
+ rc = get_vcpu_asce(vcpu, &asce, ar, mode);
if (rc)
return rc;
nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
@@ -792,11 +795,11 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
need_ipte_lock = psw_bits(*psw).t && !asce.r;
if (need_ipte_lock)
ipte_lock(vcpu);
- rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write);
+ rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, mode);
for (idx = 0; idx < nr_pages && !rc; idx++) {
gpa = *(pages + idx) + (ga & ~PAGE_MASK);
_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
- if (write)
+ if (mode == GACC_STORE)
rc = kvm_write_guest(vcpu->kvm, gpa, data, _len);
else
rc = kvm_read_guest(vcpu->kvm, gpa, data, _len);
@@ -812,7 +815,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
}
int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
- void *data, unsigned long len, int write)
+ void *data, unsigned long len, enum gacc_mode mode)
{
unsigned long _len, gpa;
int rc = 0;
@@ -820,7 +823,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
while (len && !rc) {
gpa = kvm_s390_real_to_abs(vcpu, gra);
_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
- if (write)
+ if (mode)
rc = write_guest_abs(vcpu, gpa, data, _len);
else
rc = read_guest_abs(vcpu, gpa, data, _len);
@@ -841,7 +844,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
* has to take care of this.
*/
int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
- unsigned long *gpa, int write)
+ unsigned long *gpa, enum gacc_mode mode)
{
struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -851,19 +854,19 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
gva = kvm_s390_logical_to_effective(vcpu, gva);
tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
- rc = get_vcpu_asce(vcpu, &asce, ar, write);
+ rc = get_vcpu_asce(vcpu, &asce, ar, mode);
tec->addr = gva >> PAGE_SHIFT;
if (rc)
return rc;
if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
- if (write) {
+ if (mode == GACC_STORE) {
rc = pgm->code = PGM_PROTECTION;
return rc;
}
}
if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */
- rc = guest_translate(vcpu, gva, gpa, asce, write);
+ rc = guest_translate(vcpu, gva, gpa, asce, mode);
if (rc > 0) {
if (rc == PGM_PROTECTION)
tec->b61 = 1;
@@ -883,7 +886,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
* check_gva_range - test a range of guest virtual addresses for accessibility
*/
int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
- unsigned long length, int is_write)
+ unsigned long length, enum gacc_mode mode)
{
unsigned long gpa;
unsigned long currlen;
@@ -892,7 +895,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
ipte_lock(vcpu);
while (length > 0 && !rc) {
currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE));
- rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write);
+ rc = guest_translate_address(vcpu, gva, ar, &gpa, mode);
gva += currlen;
length -= currlen;
}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index ef03726cc661..df0a79dd8159 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -155,16 +155,22 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
return kvm_read_guest(vcpu->kvm, gpa, data, len);
}
+enum gacc_mode {
+ GACC_FETCH,
+ GACC_STORE,
+ GACC_IFETCH,
+};
+
int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
- ar_t ar, unsigned long *gpa, int write);
+ ar_t ar, unsigned long *gpa, enum gacc_mode mode);
int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
- unsigned long length, int is_write);
+ unsigned long length, enum gacc_mode mode);
int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
- unsigned long len, int write);
+ unsigned long len, enum gacc_mode mode);
int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
- void *data, unsigned long len, int write);
+ void *data, unsigned long len, enum gacc_mode mode);
/**
* write_guest - copy data from kernel space to guest space
@@ -215,7 +221,7 @@ static inline __must_check
int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len)
{
- return access_guest(vcpu, ga, ar, data, len, 1);
+ return access_guest(vcpu, ga, ar, data, len, GACC_STORE);
}
/**
@@ -235,7 +241,27 @@ static inline __must_check
int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
unsigned long len)
{
- return access_guest(vcpu, ga, ar, data, len, 0);
+ return access_guest(vcpu, ga, ar, data, len, GACC_FETCH);
+}
+
+/**
+ * read_guest_instr - copy instruction data from guest space to kernel space
+ * @vcpu: virtual cpu
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from the current psw address (guest space) to @data (kernel
+ * space).
+ *
+ * The behaviour of read_guest_instr is identical to read_guest, except that
+ * instruction data will be read from primary space when in home-space or
+ * address-space mode.
+ */
+static inline __must_check
+int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len)
+{
+ return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len,
+ GACC_IFETCH);
}
/**
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index d53c10753c46..2e6b54e4d3f9 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -38,17 +38,32 @@ static const intercept_handler_t instruction_handlers[256] = {
[0xeb] = kvm_s390_handle_eb,
};
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
{
struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+ u8 ilen = 0;
- /* Use the length of the EXECUTE instruction if necessary */
- if (sie_block->icptstatus & 1) {
- ilc = (sie_block->icptstatus >> 4) & 0x6;
- if (!ilc)
- ilc = 4;
+ switch (vcpu->arch.sie_block->icptcode) {
+ case ICPT_INST:
+ case ICPT_INSTPROGI:
+ case ICPT_OPEREXC:
+ case ICPT_PARTEXEC:
+ case ICPT_IOINST:
+ /* instruction only stored for these icptcodes */
+ ilen = insn_length(vcpu->arch.sie_block->ipa >> 8);
+ /* Use the length of the EXECUTE instruction if necessary */
+ if (sie_block->icptstatus & 1) {
+ ilen = (sie_block->icptstatus >> 4) & 0x6;
+ if (!ilen)
+ ilen = 4;
+ }
+ break;
+ case ICPT_PROGI:
+ /* bit 1+2 of pgmilc are the ilc, so we directly get ilen */
+ ilen = vcpu->arch.sie_block->pgmilc & 0x6;
+ break;
}
- sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc);
+ return ilen;
}
static int handle_noop(struct kvm_vcpu *vcpu)
@@ -121,11 +136,13 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
}
-static void __extract_prog_irq(struct kvm_vcpu *vcpu,
- struct kvm_s390_pgm_info *pgm_info)
+static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu)
{
- memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info));
- pgm_info->code = vcpu->arch.sie_block->iprcc;
+ struct kvm_s390_pgm_info pgm_info = {
+ .code = vcpu->arch.sie_block->iprcc,
+ /* the PSW has already been rewound */
+ .flags = KVM_S390_PGM_FLAGS_NO_REWIND,
+ };
switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) {
case PGM_AFX_TRANSLATION:
@@ -138,7 +155,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
case PGM_PRIMARY_AUTHORITY:
case PGM_SECONDARY_AUTHORITY:
case PGM_SPACE_SWITCH:
- pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
break;
case PGM_ALEN_TRANSLATION:
case PGM_ALE_SEQUENCE:
@@ -146,7 +163,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
case PGM_ASTE_SEQUENCE:
case PGM_ASTE_VALIDITY:
case PGM_EXTENDED_AUTHORITY:
- pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+ pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
break;
case PGM_ASCE_TYPE:
case PGM_PAGE_TRANSLATION:
@@ -154,32 +171,33 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
case PGM_REGION_SECOND_TRANS:
case PGM_REGION_THIRD_TRANS:
case PGM_SEGMENT_TRANSLATION:
- pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
- pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
- pgm_info->op_access_id = vcpu->arch.sie_block->oai;
+ pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
+ pgm_info.op_access_id = vcpu->arch.sie_block->oai;
break;
case PGM_MONITOR:
- pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn;
- pgm_info->mon_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.mon_class_nr = vcpu->arch.sie_block->mcn;
+ pgm_info.mon_code = vcpu->arch.sie_block->tecmc;
break;
case PGM_VECTOR_PROCESSING:
case PGM_DATA:
- pgm_info->data_exc_code = vcpu->arch.sie_block->dxc;
+ pgm_info.data_exc_code = vcpu->arch.sie_block->dxc;
break;
case PGM_PROTECTION:
- pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
- pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+ pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+ pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
break;
default:
break;
}
if (vcpu->arch.sie_block->iprcc & PGM_PER) {
- pgm_info->per_code = vcpu->arch.sie_block->perc;
- pgm_info->per_atmid = vcpu->arch.sie_block->peratmid;
- pgm_info->per_address = vcpu->arch.sie_block->peraddr;
- pgm_info->per_access_id = vcpu->arch.sie_block->peraid;
+ pgm_info.per_code = vcpu->arch.sie_block->perc;
+ pgm_info.per_atmid = vcpu->arch.sie_block->peratmid;
+ pgm_info.per_address = vcpu->arch.sie_block->peraddr;
+ pgm_info.per_access_id = vcpu->arch.sie_block->peraid;
}
+ return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}
/*
@@ -208,7 +226,6 @@ static int handle_itdb(struct kvm_vcpu *vcpu)
static int handle_prog(struct kvm_vcpu *vcpu)
{
- struct kvm_s390_pgm_info pgm_info;
psw_t psw;
int rc;
@@ -234,8 +251,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
if (rc)
return rc;
- __extract_prog_irq(vcpu, &pgm_info);
- return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+ return inject_prog_on_prog_intercept(vcpu);
}
/**
@@ -302,7 +318,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
/* Make sure that the source is paged-in */
rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
- reg2, &srcaddr, 0);
+ reg2, &srcaddr, GACC_FETCH);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
@@ -311,14 +327,14 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
/* Make sure that the destination is paged-in */
rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
- reg1, &dstaddr, 1);
+ reg1, &dstaddr, GACC_STORE);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
if (rc != 0)
return rc;
- kvm_s390_rewind_psw(vcpu, 4);
+ kvm_s390_retry_instr(vcpu);
return 0;
}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9ffc73221792..704809d91ddd 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -182,8 +182,9 @@ static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
{
- return (vcpu->arch.sie_block->cputm >> 63) &&
- cpu_timer_interrupts_enabled(vcpu);
+ if (!cpu_timer_interrupts_enabled(vcpu))
+ return 0;
+ return kvm_s390_get_cpu_timer(vcpu) >> 63;
}
static inline int is_ioirq(unsigned long irq_type)
@@ -335,23 +336,6 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu)
set_intercept_indicators_stop(vcpu);
}
-static u16 get_ilc(struct kvm_vcpu *vcpu)
-{
- switch (vcpu->arch.sie_block->icptcode) {
- case ICPT_INST:
- case ICPT_INSTPROGI:
- case ICPT_OPEREXC:
- case ICPT_PARTEXEC:
- case ICPT_IOINST:
- /* last instruction only stored for these icptcodes */
- return insn_length(vcpu->arch.sie_block->ipa >> 8);
- case ICPT_PROGI:
- return vcpu->arch.sie_block->pgmilc;
- default:
- return 0;
- }
-}
-
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -588,7 +572,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_pgm_info pgm_info;
int rc = 0, nullifying = false;
- u16 ilc = get_ilc(vcpu);
+ u16 ilen;
spin_lock(&li->lock);
pgm_info = li->irq.pgm;
@@ -596,8 +580,9 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
memset(&li->irq.pgm, 0, sizeof(pgm_info));
spin_unlock(&li->lock);
- VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
- pgm_info.code, ilc);
+ ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
+ VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
+ pgm_info.code, ilen);
vcpu->stat.deliver_program_int++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info.code, 0);
@@ -681,10 +666,11 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
(u8 *) __LC_PER_ACCESS_ID);
}
- if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
- kvm_s390_rewind_psw(vcpu, ilc);
+ if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND))
+ kvm_s390_rewind_psw(vcpu, ilen);
- rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
+ /* bit 1+2 of the target are the ilc, so we can directly use ilen */
+ rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
(u64 *) __LC_LAST_BREAK);
rc |= put_guest_lc(vcpu, pgm_info.code,
@@ -923,9 +909,35 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
}
+static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
+{
+ u64 now, cputm, sltime = 0;
+
+ if (ckc_interrupts_enabled(vcpu)) {
+ now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+ sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+ /* already expired or overflow? */
+ if (!sltime || vcpu->arch.sie_block->ckc <= now)
+ return 0;
+ if (cpu_timer_interrupts_enabled(vcpu)) {
+ cputm = kvm_s390_get_cpu_timer(vcpu);
+ /* already expired? */
+ if (cputm >> 63)
+ return 0;
+ return min(sltime, tod_to_ns(cputm));
+ }
+ } else if (cpu_timer_interrupts_enabled(vcpu)) {
+ sltime = kvm_s390_get_cpu_timer(vcpu);
+ /* already expired? */
+ if (sltime >> 63)
+ return 0;
+ }
+ return sltime;
+}
+
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
- u64 now, sltime;
+ u64 sltime;
vcpu->stat.exit_wait_state++;
@@ -938,22 +950,20 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP; /* disabled wait */
}
- if (!ckc_interrupts_enabled(vcpu)) {
+ if (!ckc_interrupts_enabled(vcpu) &&
+ !cpu_timer_interrupts_enabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
__set_cpu_idle(vcpu);
goto no_timer;
}
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-
- /* underflow */
- if (vcpu->arch.sie_block->ckc < now)
+ sltime = __calculate_sltime(vcpu);
+ if (!sltime)
return 0;
__set_cpu_idle(vcpu);
hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
- VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
+ VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
no_timer:
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
kvm_vcpu_block(vcpu);
@@ -980,18 +990,16 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
struct kvm_vcpu *vcpu;
- u64 now, sltime;
+ u64 sltime;
vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+ sltime = __calculate_sltime(vcpu);
/*
* If the monotonic clock runs faster than the tod clock we might be
* woken up too early and have to go back to sleep to avoid deadlocks.
*/
- if (vcpu->arch.sie_block->ckc > now &&
- hrtimer_forward_now(timer, ns_to_ktime(sltime)))
+ if (sltime && hrtimer_forward_now(timer, ns_to_ktime(sltime)))
return HRTIMER_RESTART;
kvm_s390_vcpu_wakeup(vcpu);
return HRTIMER_NORESTART;
@@ -1059,8 +1067,16 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
irq->u.pgm.code, 0);
+ if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) {
+ /* auto detection if no valid ILC was given */
+ irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK;
+ irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu);
+ irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID;
+ }
+
if (irq->u.pgm.code == PGM_PER) {
li->irq.pgm.code |= PGM_PER;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify PER related information */
li->irq.pgm.per_address = irq->u.pgm.per_address;
li->irq.pgm.per_code = irq->u.pgm.per_code;
@@ -1069,6 +1085,7 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
} else if (!(irq->u.pgm.code & PGM_PER)) {
li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) |
irq->u.pgm.code;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify non-PER information */
li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code;
li->irq.pgm.mon_code = irq->u.pgm.mon_code;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 03dfe9c667f4..e196582fe87d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -158,6 +158,8 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
kvm->arch.epoch -= *delta;
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.sie_block->epoch -= *delta;
+ if (vcpu->arch.cputm_enabled)
+ vcpu->arch.cputm_start += *delta;
}
}
return NOTIFY_OK;
@@ -274,7 +276,6 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
unsigned long address;
struct gmap *gmap = kvm->arch.gmap;
- down_read(&gmap->mm->mmap_sem);
/* Loop over all guest pages */
last_gfn = memslot->base_gfn + memslot->npages;
for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
@@ -282,8 +283,10 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
if (gmap_test_and_clear_dirty(address, gmap))
mark_page_dirty(kvm, cur_gfn);
+ if (fatal_signal_pending(current))
+ return;
+ cond_resched();
}
- up_read(&gmap->mm->mmap_sem);
}
/* Section: vm related */
@@ -352,8 +355,8 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
if (atomic_read(&kvm->online_vcpus)) {
r = -EBUSY;
} else if (MACHINE_HAS_VX) {
- set_kvm_facility(kvm->arch.model.fac->mask, 129);
- set_kvm_facility(kvm->arch.model.fac->list, 129);
+ set_kvm_facility(kvm->arch.model.fac_mask, 129);
+ set_kvm_facility(kvm->arch.model.fac_list, 129);
r = 0;
} else
r = -EINVAL;
@@ -367,8 +370,8 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
if (atomic_read(&kvm->online_vcpus)) {
r = -EBUSY;
} else if (test_facility(64)) {
- set_kvm_facility(kvm->arch.model.fac->mask, 64);
- set_kvm_facility(kvm->arch.model.fac->list, 64);
+ set_kvm_facility(kvm->arch.model.fac_mask, 64);
+ set_kvm_facility(kvm->arch.model.fac_list, 64);
r = 0;
}
mutex_unlock(&kvm->lock);
@@ -651,7 +654,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
memcpy(&kvm->arch.model.cpu_id, &proc->cpuid,
sizeof(struct cpuid));
kvm->arch.model.ibc = proc->ibc;
- memcpy(kvm->arch.model.fac->list, proc->fac_list,
+ memcpy(kvm->arch.model.fac_list, proc->fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
} else
ret = -EFAULT;
@@ -685,7 +688,8 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
}
memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid));
proc->ibc = kvm->arch.model.ibc;
- memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE);
+ memcpy(&proc->fac_list, kvm->arch.model.fac_list,
+ S390_ARCH_FAC_LIST_SIZE_BYTE);
if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
ret = -EFAULT;
kfree(proc);
@@ -705,7 +709,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
}
get_cpu_id((struct cpuid *) &mach->cpuid);
mach->ibc = sclp.ibc;
- memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
+ memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
@@ -1082,16 +1086,12 @@ static void kvm_s390_get_cpu_id(struct cpuid *cpu_id)
cpu_id->version = 0xff;
}
-static int kvm_s390_crypto_init(struct kvm *kvm)
+static void kvm_s390_crypto_init(struct kvm *kvm)
{
if (!test_kvm_facility(kvm, 76))
- return 0;
-
- kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb),
- GFP_KERNEL | GFP_DMA);
- if (!kvm->arch.crypto.crycb)
- return -ENOMEM;
+ return;
+ kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
kvm_s390_set_crycb_format(kvm);
/* Enable AES/DEA protected key functions by default */
@@ -1101,8 +1101,6 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
-
- return 0;
}
static void sca_dispose(struct kvm *kvm)
@@ -1156,37 +1154,30 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (!kvm->arch.dbf)
goto out_err;
- /*
- * The architectural maximum amount of facilities is 16 kbit. To store
- * this amount, 2 kbyte of memory is required. Thus we need a full
- * page to hold the guest facility list (arch.model.fac->list) and the
- * facility mask (arch.model.fac->mask). Its address size has to be
- * 31 bits and word aligned.
- */
- kvm->arch.model.fac =
- (struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
- if (!kvm->arch.model.fac)
+ kvm->arch.sie_page2 =
+ (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+ if (!kvm->arch.sie_page2)
goto out_err;
/* Populate the facility mask initially. */
- memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
+ memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
if (i < kvm_s390_fac_list_mask_size())
- kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i];
+ kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
else
- kvm->arch.model.fac->mask[i] = 0UL;
+ kvm->arch.model.fac_mask[i] = 0UL;
}
/* Populate the facility list initially. */
- memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask,
+ kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
+ memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
kvm->arch.model.ibc = sclp.ibc & 0x0fff;
- if (kvm_s390_crypto_init(kvm) < 0)
- goto out_err;
+ kvm_s390_crypto_init(kvm);
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
@@ -1222,8 +1213,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
return 0;
out_err:
- kfree(kvm->arch.crypto.crycb);
- free_page((unsigned long)kvm->arch.model.fac);
+ free_page((unsigned long)kvm->arch.sie_page2);
debug_unregister(kvm->arch.dbf);
sca_dispose(kvm);
KVM_EVENT(3, "creation of vm failed: %d", rc);
@@ -1269,10 +1259,9 @@ static void kvm_free_vcpus(struct kvm *kvm)
void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_free_vcpus(kvm);
- free_page((unsigned long)kvm->arch.model.fac);
sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
- kfree(kvm->arch.crypto.crycb);
+ free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
gmap_free(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
@@ -1414,8 +1403,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
KVM_SYNC_PFAULT;
if (test_kvm_facility(vcpu->kvm, 64))
vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
- if (test_kvm_facility(vcpu->kvm, 129))
+ /* fprs can be synchronized via vrs, even if the guest has no vx. With
+ * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+ */
+ if (MACHINE_HAS_VX)
vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+ else
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
if (kvm_is_ucontrol(vcpu->kvm))
return __kvm_ucontrol_vcpu_init(vcpu);
@@ -1423,6 +1417,93 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
return 0;
}
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ WARN_ON_ONCE(vcpu->arch.cputm_start != 0);
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ vcpu->arch.cputm_start = get_tod_clock_fast();
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __stop_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ WARN_ON_ONCE(vcpu->arch.cputm_start == 0);
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ vcpu->arch.sie_block->cputm -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+ vcpu->arch.cputm_start = 0;
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ WARN_ON_ONCE(vcpu->arch.cputm_enabled);
+ vcpu->arch.cputm_enabled = true;
+ __start_cpu_timer_accounting(vcpu);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ WARN_ON_ONCE(!vcpu->arch.cputm_enabled);
+ __stop_cpu_timer_accounting(vcpu);
+ vcpu->arch.cputm_enabled = false;
+}
+
+static void enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ __enable_cpu_timer_accounting(vcpu);
+ preempt_enable();
+}
+
+static void disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ __disable_cpu_timer_accounting(vcpu);
+ preempt_enable();
+}
+
+/* set the cpu timer - may only be called from the VCPU thread itself */
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm)
+{
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ if (vcpu->arch.cputm_enabled)
+ vcpu->arch.cputm_start = get_tod_clock_fast();
+ vcpu->arch.sie_block->cputm = cputm;
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+ preempt_enable();
+}
+
+/* update and get the cpu timer - can also be called from other VCPU threads */
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
+{
+ unsigned int seq;
+ __u64 value;
+
+ if (unlikely(!vcpu->arch.cputm_enabled))
+ return vcpu->arch.sie_block->cputm;
+
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ do {
+ seq = raw_read_seqcount(&vcpu->arch.cputm_seqcount);
+ /*
+ * If the writer would ever execute a read in the critical
+ * section, e.g. in irq context, we have a deadlock.
+ */
+ WARN_ON_ONCE((seq & 1) && smp_processor_id() == vcpu->cpu);
+ value = vcpu->arch.sie_block->cputm;
+ /* if cputm_start is 0, accounting is being started/stopped */
+ if (likely(vcpu->arch.cputm_start))
+ value -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+ } while (read_seqcount_retry(&vcpu->arch.cputm_seqcount, seq & ~1));
+ preempt_enable();
+ return value;
+}
+
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
/* Save host register state */
@@ -1430,10 +1511,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
- /* Depending on MACHINE_HAS_VX, data stored to vrs either
- * has vector register or floating point register format.
- */
- current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+ if (MACHINE_HAS_VX)
+ current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+ else
+ current->thread.fpu.regs = vcpu->run->s.regs.fprs;
current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
if (test_fp_ctl(current->thread.fpu.fpc))
/* User space provided an invalid FPC, let's clear it */
@@ -1443,10 +1524,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
restore_access_regs(vcpu->run->s.regs.acrs);
gmap_enable(vcpu->arch.gmap);
atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+ __start_cpu_timer_accounting(vcpu);
+ vcpu->cpu = cpu;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ vcpu->cpu = -1;
+ if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+ __stop_cpu_timer_accounting(vcpu);
atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
gmap_disable(vcpu->arch.gmap);
@@ -1468,7 +1555,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->gpsw.mask = 0UL;
vcpu->arch.sie_block->gpsw.addr = 0UL;
kvm_s390_set_prefix(vcpu, 0);
- vcpu->arch.sie_block->cputm = 0UL;
+ kvm_s390_set_cpu_timer(vcpu, 0);
vcpu->arch.sie_block->ckc = 0UL;
vcpu->arch.sie_block->todpr = 0;
memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
@@ -1538,7 +1625,8 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
vcpu->arch.cpu_id = model->cpu_id;
vcpu->arch.sie_block->ibc = model->ibc;
- vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
+ if (test_kvm_facility(vcpu->kvm, 7))
+ vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
}
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -1616,6 +1704,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
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;
+ seqcount_init(&vcpu->arch.cputm_seqcount);
rc = kvm_vcpu_init(vcpu, kvm, id);
if (rc)
@@ -1715,7 +1804,7 @@ static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CPU_TIMER:
- r = put_user(vcpu->arch.sie_block->cputm,
+ r = put_user(kvm_s390_get_cpu_timer(vcpu),
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CLOCK_COMP:
@@ -1753,6 +1842,7 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
struct kvm_one_reg *reg)
{
int r = -EINVAL;
+ __u64 val;
switch (reg->id) {
case KVM_REG_S390_TODPR:
@@ -1764,8 +1854,9 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CPU_TIMER:
- r = get_user(vcpu->arch.sie_block->cputm,
- (u64 __user *)reg->addr);
+ r = get_user(val, (u64 __user *)reg->addr);
+ if (!r)
+ kvm_s390_set_cpu_timer(vcpu, val);
break;
case KVM_REG_S390_CLOCK_COMP:
r = get_user(vcpu->arch.sie_block->ckc,
@@ -2158,8 +2249,10 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
{
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
- u8 opcode;
+ struct kvm_s390_pgm_info pgm_info = {
+ .code = PGM_ADDRESSING,
+ };
+ u8 opcode, ilen;
int rc;
VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
@@ -2173,12 +2266,21 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
* to look up the current opcode to get the length of the instruction
* to be able to forward the PSW.
*/
- rc = read_guest(vcpu, psw->addr, 0, &opcode, 1);
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- psw->addr = __rewind_psw(*psw, -insn_length(opcode));
-
- return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ rc = read_guest_instr(vcpu, &opcode, 1);
+ ilen = insn_length(opcode);
+ if (rc < 0) {
+ return rc;
+ } else if (rc) {
+ /* Instruction-Fetching Exceptions - we can't detect the ilen.
+ * Forward by arbitrary ilc, injection will take care of
+ * nullification if necessary.
+ */
+ pgm_info = vcpu->arch.pgm;
+ ilen = 4;
+ }
+ pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID;
+ kvm_s390_forward_psw(vcpu, ilen);
+ return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
@@ -2244,10 +2346,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
*/
local_irq_disable();
__kvm_guest_enter();
+ __disable_cpu_timer_accounting(vcpu);
local_irq_enable();
exit_reason = sie64a(vcpu->arch.sie_block,
vcpu->run->s.regs.gprs);
local_irq_disable();
+ __enable_cpu_timer_accounting(vcpu);
__kvm_guest_exit();
local_irq_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
@@ -2271,7 +2375,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
- vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm;
+ kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
@@ -2293,7 +2397,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
- kvm_run->s.regs.cputm = vcpu->arch.sie_block->cputm;
+ kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
@@ -2325,6 +2429,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
sync_regs(vcpu, kvm_run);
+ enable_cpu_timer_accounting(vcpu);
might_fault();
rc = __vcpu_run(vcpu);
@@ -2344,6 +2449,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
rc = 0;
}
+ disable_cpu_timer_accounting(vcpu);
store_regs(vcpu, kvm_run);
if (vcpu->sigset_active)
@@ -2364,7 +2470,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
unsigned char archmode = 1;
freg_t fprs[NUM_FPRS];
unsigned int px;
- u64 clkcomp;
+ u64 clkcomp, cputm;
int rc;
px = kvm_s390_get_prefix(vcpu);
@@ -2386,7 +2492,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
fprs, 128);
} else {
rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
- vcpu->run->s.regs.vrs, 128);
+ vcpu->run->s.regs.fprs, 128);
}
rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
vcpu->run->s.regs.gprs, 128);
@@ -2398,8 +2504,9 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
&vcpu->run->s.regs.fpc, 4);
rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
&vcpu->arch.sie_block->todpr, 4);
+ cputm = kvm_s390_get_cpu_timer(vcpu);
rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
- &vcpu->arch.sie_block->cputm, 8);
+ &cputm, 8);
clkcomp = vcpu->arch.sie_block->ckc >> 8;
rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
&clkcomp, 8);
@@ -2605,7 +2712,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
switch (mop->op) {
case KVM_S390_MEMOP_LOGICAL_READ:
if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+ mop->size, GACC_FETCH);
break;
}
r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
@@ -2616,7 +2724,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
break;
case KVM_S390_MEMOP_LOGICAL_WRITE:
if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+ mop->size, GACC_STORE);
break;
}
if (copy_from_user(tmpbuf, uaddr, mop->size)) {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index df1abada1f36..8621ab00ec8e 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -19,6 +19,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/facility.h>
+#include <asm/processor.h>
typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
@@ -53,6 +54,11 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
}
+static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
+{
+ return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_WAIT;
+}
+
static inline int kvm_is_ucontrol(struct kvm *kvm)
{
#ifdef CONFIG_KVM_S390_UCONTROL
@@ -154,8 +160,8 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
/* test availability of facility in a kvm instance */
static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr)
{
- return __test_facility(nr, kvm->arch.model.fac->mask) &&
- __test_facility(nr, kvm->arch.model.fac->list);
+ return __test_facility(nr, kvm->arch.model.fac_mask) &&
+ __test_facility(nr, kvm->arch.model.fac_list);
}
static inline int set_kvm_facility(u64 *fac_list, unsigned long nr)
@@ -212,8 +218,22 @@ int kvm_s390_reinject_io_int(struct kvm *kvm,
int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
/* implemented in intercept.c */
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc);
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu);
int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+static inline void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+ struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+
+ sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilen);
+}
+static inline void kvm_s390_forward_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+ kvm_s390_rewind_psw(vcpu, -ilen);
+}
+static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu)
+{
+ kvm_s390_rewind_psw(vcpu, kvm_s390_get_ilen(vcpu));
+}
/* implemented in priv.c */
int is_valid_psw(psw_t *psw);
@@ -248,6 +268,8 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
unsigned long kvm_s390_fac_list_mask_size(void);
extern unsigned long kvm_s390_fac_list_mask[];
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
/* implemented in diag.c */
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ed74e86d9b9e..f218ccf016c8 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -173,7 +173,7 @@ static int handle_skey(struct kvm_vcpu *vcpu)
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- kvm_s390_rewind_psw(vcpu, 4);
+ kvm_s390_retry_instr(vcpu);
VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
return 0;
}
@@ -184,7 +184,7 @@ static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
if (psw_bits(vcpu->arch.sie_block->gpsw).p)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
- kvm_s390_rewind_psw(vcpu, 4);
+ kvm_s390_retry_instr(vcpu);
VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
return 0;
}
@@ -354,7 +354,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
* We need to shift the lower 32 facility bits (bit 0-31) from a u64
* into a u32 memory representation. They will remain bits 0-31.
*/
- fac = *vcpu->kvm->arch.model.fac->list >> 32;
+ fac = *vcpu->kvm->arch.model.fac_list >> 32;
rc = write_guest_lc(vcpu, offsetof(struct lowcore, stfl_fac_list),
&fac, sizeof(fac));
if (rc)
@@ -759,8 +759,8 @@ static int handle_essa(struct kvm_vcpu *vcpu)
if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- /* Rewind PSW to repeat the ESSA instruction */
- kvm_s390_rewind_psw(vcpu, 4);
+ /* Retry the ESSA instruction */
+ kvm_s390_retry_instr(vcpu);
vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */
cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
down_read(&gmap->mm->mmap_sem);
@@ -981,11 +981,12 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
ipte_lock(vcpu);
- ret = guest_translate_address(vcpu, address1, ar, &gpa, 1);
+ ret = guest_translate_address(vcpu, address1, ar, &gpa, GACC_STORE);
if (ret == PGM_PROTECTION) {
/* Write protected? Try again with read-only... */
cc = 1;
- ret = guest_translate_address(vcpu, address1, ar, &gpa, 0);
+ ret = guest_translate_address(vcpu, address1, ar, &gpa,
+ GACC_FETCH);
}
if (ret) {
if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) {