Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-12-03 01:21:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

KVM: s390: Features and fixes for 4.1 (kvm/next)

Browse Source 
1. Fixes
 2. Implement access register mode in KVM
 3. Provide a userspace post handler for the STSI instruction
 4. Provide an interface for compliant memory accesses
 5. Provide an interface for getting/setting the guest storage key
 6. Fixup for the vector facility patches: do not announce the
    vector facility in the guest for old QEMUs.
 
 1-5 were initially shown as RFC in
 
 http://www.spinics.net/lists/kvm/msg114720.html
 
 some small review changes
 - added some ACKs
 - have the AR mode patches first
 - get rid of unnecessary AR_INVAL define
 - typos and language
 
 6. two new patches
 The two new patches fixup the vector support patches that were
 introduced in the last pull request for QEMU versions that dont
 know about vector support and guests that do. (We announce the
 facility bit, but dont enable the facility so vector aware guests
 will crash on vector instructions).
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.14 (GNU/Linux)
 
 iQIcBAABAgAGBQJVCV7NAAoJEBF7vIC1phx8ymcP/RovYmBGd7e6jBZLx4fooc97
 DFuMkEdNT3bkA0x/L+SgYcExFkoAUX5KPK74mHOTmmBZHopX1AMDKQyEDacjNWBb
 9CJdPffJWKKjFtC7KwrkgnDKBrOsmNLdWsLtl8aEIAxxKznvLXYsrvMrBYqdRkUh
 nJsjaQueKP8AbzSLsG9N3Yilps2988VMo+wArfw0jVCCO+sWNZnYYsMXwRgyQsPb
 K5+0Co/cw1wfnzy1hUWqpRWs26JLIcewLnMx9Ycoaap1V0A59t8J/9xPDHHODX3d
 2wXlJsiNmoJj/kqakT4xlNTS0q7Tn2iLlJ1NNUADScR3zP7twXs17H2g8hGSVRiM
 xBd0s671m4eSZB5Bk3LSf0PPLbOmTnCB1qYpXhd56an3MGbYIzRtcmU9LvbY3SzH
 yxsVUGww1uvYN6A5RABDjqrbmnl9eQ4HruNUnA/fHLS6sDtYbmi7ln4bV3eE1sPa
 0r7lPYKWdvyN0FO3Rb9Qwnjhd3F/uaLTWjptdLXapRLO0fD8adiYqzWmbXMZrgcD
 BU1CNejIIYP/GZDOQanJoVQJWd9akUW/s6QiDMJRc87KaL13/cCWoicPi1j62ygj
 gueYjz1KfKh6hoVvviTl2NgyXke2qs+bIKDrRV6VfdIgfeSN50lUxdJm61RdDA9d
 IPrxUJDy8YdzH7rcMPXP
 =GqOj
 -----END PGP SIGNATURE-----

Merge tag 'kvm-s390-next-20150318' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into queue

KVM: s390: Features and fixes for 4.1 (kvm/next)

1. Fixes
2. Implement access register mode in KVM
3. Provide a userspace post handler for the STSI instruction
4. Provide an interface for compliant memory accesses
5. Provide an interface for getting/setting the guest storage key
6. Fixup for the vector facility patches: do not announce the
   vector facility in the guest for old QEMUs.

1-5 were initially shown as RFC in

http://www.spinics.net/lists/kvm/msg114720.html

some small review changes
- added some ACKs
- have the AR mode patches first
- get rid of unnecessary AR_INVAL define
- typos and language

6. two new patches
The two new patches fixup the vector support patches that were
introduced in the last pull request for QEMU versions that dont
know about vector support and guests that do. (We announce the
facility bit, but dont enable the facility so vector aware guests
will crash on vector instructions).
This commit is contained in:
Marcelo Tosatti 2015-03-23 20:32:02 -03:00 committed by Marcelo Tosatti
commit bbf4aef89d
11 changed files with 755 additions and 127 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

132
Documentation/virtual/kvm/api.txt
View File

@ -2716,6 +2716,110 @@ The fields in each entry are defined as follows:
eax, ebx, ecx, edx: the values returned by the cpuid instruction for
this function/index combination
4.89 KVM_S390_MEM_OP
Capability: KVM_CAP_S390_MEM_OP
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_mem_op (in)
Returns: = 0 on success,
< 0 on generic error (e.g. -EFAULT or -ENOMEM),
> 0 if an exception occurred while walking the page tables
Read or write data from/to the logical (virtual) memory of a VPCU.
Parameters are specified via the following structure:
struct kvm_s390_mem_op {
__u64 gaddr; /* the guest address */
__u64 flags; /* flags */
__u32 size; /* amount of bytes */
__u32 op; /* type of operation */
__u64 buf; /* buffer in userspace */
__u8 ar; /* the access register number */
__u8 reserved[31]; /* should be set to 0 */
};
The type of operation is specified in the "op" field. It is either
KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or
KVM_S390_MEMOP_LOGICAL_WRITE for writing to logical memory space. The
KVM_S390_MEMOP_F_CHECK_ONLY flag can be set in the "flags" field to check
whether the corresponding memory access would create an access exception
(without touching the data in the memory at the destination). In case an
access exception occurred while walking the MMU tables of the guest, the
ioctl returns a positive error number to indicate the type of exception.
This exception is also raised directly at the corresponding VCPU if the
flag KVM_S390_MEMOP_F_INJECT_EXCEPTION is set in the "flags" field.
The start address of the memory region has to be specified in the "gaddr"
field, and the length of the region in the "size" field. "buf" is the buffer
supplied by the userspace application where the read data should be written
to for KVM_S390_MEMOP_LOGICAL_READ, or where the data that should be written
is stored for a KVM_S390_MEMOP_LOGICAL_WRITE. "buf" is unused and can be NULL
when KVM_S390_MEMOP_F_CHECK_ONLY is specified. "ar" designates the access
register number to be used.
The "reserved" field is meant for future extensions. It is not used by
KVM with the currently defined set of flags.
4.90 KVM_S390_GET_SKEYS
Capability: KVM_CAP_S390_SKEYS
Architectures: s390
Type: vm ioctl
Parameters: struct kvm_s390_skeys
Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
keys, negative value on error
This ioctl is used to get guest storage key values on the s390
architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
struct kvm_s390_skeys {
__u64 start_gfn;
__u64 count;
__u64 skeydata_addr;
__u32 flags;
__u32 reserved[9];
};
The start_gfn field is the number of the first guest frame whose storage keys
you want to get.
The count field is the number of consecutive frames (starting from start_gfn)
whose storage keys to get. The count field must be at least 1 and the maximum
allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
will cause the ioctl to return -EINVAL.
The skeydata_addr field is the address to a buffer large enough to hold count
bytes. This buffer will be filled with storage key data by the ioctl.
4.91 KVM_S390_SET_SKEYS
Capability: KVM_CAP_S390_SKEYS
Architectures: s390
Type: vm ioctl
Parameters: struct kvm_s390_skeys
Returns: 0 on success, negative value on error
This ioctl is used to set guest storage key values on the s390
architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
See section on KVM_S390_GET_SKEYS for struct definition.
The start_gfn field is the number of the first guest frame whose storage keys
you want to set.
The count field is the number of consecutive frames (starting from start_gfn)
whose storage keys to get. The count field must be at least 1 and the maximum
allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
will cause the ioctl to return -EINVAL.
The skeydata_addr field is the address to a buffer containing count bytes of
storage keys. Each byte in the buffer will be set as the storage key for a
single frame starting at start_gfn for count frames.
Note: If any architecturally invalid key value is found in the given data then
the ioctl will return -EINVAL.
5. The kvm_run structure
------------------------
@ -3258,3 +3362,31 @@ Returns: 0 on success, negative value on error
Allows use of the vector registers introduced with z13 processor, and
provides for the synchronization between host and user space. Will
return -EINVAL if the machine does not support vectors.
7.4 KVM_CAP_S390_USER_STSI
Architectures: s390
Parameters: none
This capability allows post-handlers for the STSI instruction. After
initial handling in the kernel, KVM exits to user space with
KVM_EXIT_S390_STSI to allow user space to insert further data.
Before exiting to userspace, kvm handlers should fill in s390_stsi field of
vcpu->run:
struct {
__u64 addr;
__u8 ar;
__u8 reserved;
__u8 fc;
__u8 sel1;
__u16 sel2;
} s390_stsi;
@addr - guest address of STSI SYSIB
@fc - function code
@sel1 - selector 1
@sel2 - selector 2
@ar - access register number
KVM handlers should exit to userspace with rc = -EREMOTE.

2
arch/s390/include/asm/kvm_host.h
View File

@ -562,9 +562,9 @@ struct kvm_arch{
int css_support;
int use_irqchip;
int use_cmma;
int use_vectors;
int user_cpu_state_ctrl;
int user_sigp;
int user_stsi;
struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
wait_queue_head_t ipte_wq;
int ipte_lock_count;

4
arch/s390/kvm/diag.c
View File

@ -77,7 +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)
@ -230,7 +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);

294
arch/s390/kvm/gaccess.c
View File

@ -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;
@ -207,6 +208,54 @@ union raddress {
unsigned long pfra : 52; /* Page-Frame Real Address */
};
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)
{
@ -307,15 +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;
}
@ -330,6 +521,7 @@ 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
@ -345,7 +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};
@ -354,12 +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_kvm_facility(vcpu->kvm, 8);
edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78);
asce.val = get_vcpu_asce(vcpu);
if (asce.r)
goto real_address;
ptr = asce.origin * 4096;
@ -506,48 +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;
@ -557,7 +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)
@ -578,7 +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;
@ -591,20 +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);
@ -652,7 +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;
@ -661,26 +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;
@ -697,28 +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;

21
arch/s390/kvm/gaccess.h
View File

@ -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 */

4
arch/s390/kvm/intercept.c
View File

@ -320,7 +320,7 @@ 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],
&srcaddr, 0);
reg2, &srcaddr, 0);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
@ -329,7 +329,7 @@ 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],
&dstaddr, 1);
reg1, &dstaddr, 1);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);

244
arch/s390/kvm/kvm-s390.c
View File

@ -25,6 +25,7 @@
#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>
@ -38,6 +39,8 @@
#include "trace.h"
#include "trace-s390.h"
#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
struct kvm_stats_debugfs_item debugfs_entries[] = {
@ -104,7 +107,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
unsigned long kvm_s390_fac_list_mask[] = {
0xff82fffbf4fc2000UL,
0x005c000000000000UL,
0x4000000000000000UL,
};
unsigned long kvm_s390_fac_list_mask_size(void)
@ -175,8 +177,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_VM_ATTRIBUTES:
case KVM_CAP_MP_STATE:
case KVM_CAP_S390_USER_SIGP:
case KVM_CAP_S390_USER_STSI:
case KVM_CAP_S390_SKEYS:
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;
@ -271,8 +278,16 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
r = 0;
break;
case KVM_CAP_S390_VECTOR_REGISTERS:
kvm->arch.use_vectors = MACHINE_HAS_VX;
r = MACHINE_HAS_VX ? 0 : -EINVAL;
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;
@ -718,6 +733,108 @@ 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)
{
@ -777,6 +894,26 @@ 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;
}
@ -897,7 +1034,7 @@ 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
@ -909,7 +1046,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.model.fac =
(struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
if (!kvm->arch.model.fac)
goto out_nofac;
goto out_err;
/* Populate the facility mask initially. */
memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
@ -929,7 +1066,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff;
if (kvm_s390_crypto_init(kvm) < 0)
goto out_crypto;
goto out_err;
spin_lock_init(&kvm->arch.float_int.lock);
INIT_LIST_HEAD(&kvm->arch.float_int.list);
@ -944,28 +1081,23 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
} else {
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.use_vectors = 0;
kvm->arch.epoch = 0;
spin_lock_init(&kvm->arch.start_stop_lock);
return 0;
out_nogmap:
kfree(kvm->arch.crypto.crycb);
out_crypto:
free_page((unsigned long)kvm->arch.model.fac);
out_nofac:
debug_unregister(kvm->arch.dbf);
out_nodbf:
free_page((unsigned long)(kvm->arch.sca));
out_err:
kfree(kvm->arch.crypto.crycb);
free_page((unsigned long)kvm->arch.model.fac);
debug_unregister(kvm->arch.dbf);
free_page((unsigned long)(kvm->arch.sca));
return rc;
}
@ -1057,12 +1189,12 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
if (vcpu->kvm->arch.use_vectors)
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);
if (vcpu->kvm->arch.use_vectors) {
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 {
@ -1078,7 +1210,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
gmap_disable(vcpu->arch.gmap);
if (vcpu->kvm->arch.use_vectors) {
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 {
@ -1087,7 +1219,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
}
save_access_regs(vcpu->run->s.regs.acrs);
restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
if (vcpu->kvm->arch.use_vectors)
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);
@ -1187,7 +1319,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->eca |= 1;
if (sclp_has_sigpif())
vcpu->arch.sie_block->eca |= 0x10000000U;
if (vcpu->kvm->arch.use_vectors) {
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
vcpu->arch.sie_block->ecd |= 0x20000000;
}
@ -1780,7 +1912,7 @@ 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, &opcode, 1);
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));
@ -2189,6 +2321,65 @@ 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)
{
@ -2288,6 +2479,15 @@ 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;
}
default:
r = -ENOTTY;
}

38
arch/s390/kvm/kvm-s390.h
View File

@ -70,16 +70,22 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
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;
@ -88,6 +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)
@ -98,7 +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) +
@ -107,14 +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;
}
@ -125,13 +142,24 @@ 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 intance */
/* 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)
{

93
arch/s390/kvm/priv.c
View File

@ -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);
@ -207,7 +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);
@ -231,8 +235,9 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
u32 tpi_data[3];
int rc;
u64 addr;
ar_t ar;
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);
@ -251,7 +256,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
* provided area.
*/
len = sizeof(tpi_data) - 4;
rc = write_guest(vcpu, addr, &tpi_data, len);
rc = write_guest(vcpu, addr, ar, &tpi_data, len);
if (rc) {
rc = kvm_s390_inject_prog_cond(vcpu, rc);
goto reinject_interrupt;
@ -395,15 +400,16 @@ 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))
@ -421,14 +427,15 @@ 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;
@ -442,18 +449,19 @@ 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);
@ -488,6 +496,17 @@ 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;
@ -496,6 +515,7 @@ 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);
@ -518,7 +538,7 @@ 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);
@ -542,16 +562,20 @@ 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:
@ -680,7 +704,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
}
if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
if (kvm_s390_check_low_addr_protection(vcpu, start))
if (kvm_s390_check_low_addr_prot_real(vcpu, start))
return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
}
@ -786,13 +810,14 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
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);
@ -801,7 +826,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga);
nr_regs = ((reg3 - reg1) & 0xf) + 1;
rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32));
rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
reg = reg1;
@ -824,13 +849,14 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
int reg, rc, nr_regs;
u32 ctl_array[16];
u64 ga;
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);
@ -846,7 +872,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
break;
reg = (reg + 1) % 16;
} while (1);
rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32));
rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32));
return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
}
@ -857,13 +883,14 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
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);
@ -872,7 +899,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga);
nr_regs = ((reg3 - reg1) & 0xf) + 1;
rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64));
rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
reg = reg1;
@ -894,13 +921,14 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
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);
@ -916,7 +944,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
break;
reg = (reg + 1) % 16;
} while (1);
rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64));
rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64));
return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
}
@ -941,13 +969,14 @@ 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
@ -956,11 +985,11 @@ 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) {

4
arch/s390/kvm/sigp.c
View File

@ -434,7 +434,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
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);
order_code = kvm_s390_get_base_disp_rs(vcpu, NULL);
if (handle_sigp_order_in_user_space(vcpu, order_code))
return -EOPNOTSUPP;
@ -476,7 +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);

46
include/uapi/linux/kvm.h
View File

@ -147,6 +147,16 @@ struct kvm_pit_config {
#define KVM_PIT_SPEAKER_DUMMY 1
struct kvm_s390_skeys {
__u64 start_gfn;
__u64 count;
__u64 skeydata_addr;
__u32 flags;
__u32 reserved[9];
};
#define KVM_S390_GET_SKEYS_NONE 1
#define KVM_S390_SKEYS_MAX 1048576
#define KVM_EXIT_UNKNOWN 0
#define KVM_EXIT_EXCEPTION 1
#define KVM_EXIT_IO 2
@ -172,6 +182,7 @@ struct kvm_pit_config {
#define KVM_EXIT_S390_TSCH 22
#define KVM_EXIT_EPR 23
#define KVM_EXIT_SYSTEM_EVENT 24
#define KVM_EXIT_S390_STSI 25
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@ -309,6 +320,15 @@ struct kvm_run {
__u32 type;
__u64 flags;
} system_event;
/* KVM_EXIT_S390_STSI */
struct {
__u64 addr;
__u8 ar;
__u8 reserved;
__u8 fc;
__u8 sel1;
__u16 sel2;
} s390_stsi;
/* Fix the size of the union. */
char padding[256];
};
@ -365,6 +385,24 @@ struct kvm_translation {
__u8 pad[5];
};
/* for KVM_S390_MEM_OP */
struct kvm_s390_mem_op {
/* in */
__u64 gaddr; /* the guest address */
__u64 flags; /* flags */
__u32 size; /* amount of bytes */
__u32 op; /* type of operation */
__u64 buf; /* buffer in userspace */
__u8 ar; /* the access register number */
__u8 reserved[31]; /* should be set to 0 */
};
/* types for kvm_s390_mem_op->op */
#define KVM_S390_MEMOP_LOGICAL_READ 0
#define KVM_S390_MEMOP_LOGICAL_WRITE 1
/* flags for kvm_s390_mem_op->flags */
#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
/* for KVM_INTERRUPT */
struct kvm_interrupt {
/* in */
@ -761,6 +799,9 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_CHECK_EXTENSION_VM 105
#define KVM_CAP_S390_USER_SIGP 106
#define KVM_CAP_S390_VECTOR_REGISTERS 107
#define KVM_CAP_S390_MEM_OP 108
#define KVM_CAP_S390_USER_STSI 109
#define KVM_CAP_S390_SKEYS 110
#ifdef KVM_CAP_IRQ_ROUTING
@ -1136,6 +1177,11 @@ struct kvm_s390_ucas_mapping {
#define KVM_ARM_VCPU_INIT _IOW(KVMIO, 0xae, struct kvm_vcpu_init)
#define KVM_ARM_PREFERRED_TARGET _IOR(KVMIO, 0xaf, struct kvm_vcpu_init)
#define KVM_GET_REG_LIST _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
/* Available with KVM_CAP_S390_MEM_OP */
#define KVM_S390_MEM_OP _IOW(KVMIO, 0xb1, struct kvm_s390_mem_op)
/* Available with KVM_CAP_S390_SKEYS */
#define KVM_S390_GET_SKEYS _IOW(KVMIO, 0xb2, struct kvm_s390_skeys)
#define KVM_S390_SET_SKEYS _IOW(KVMIO, 0xb3, struct kvm_s390_skeys)
#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)