UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

KVM: s390/pci: enable zPCI for interpretive execution 

Add the necessary code in s390 base, pci and KVM to enable interpretion
 of PCI pasthru.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE+SKTgaM0CPnbq/vKEXu8gLWmHHwFAmLL7HcACgkQEXu8gLWm
 HHz0JA/8C/pG5JdeOfKA6ZgWuUtxh8NRAmn+XEh+sAPpdK1cmEc1Qt/UKteSFel4
 cmqfaCELalq/BaFxtPS7Wn8Rf4pY8/GwEzwM0dNiS09pTWv0YMXql6+013nr1TJU
 hWx5Pm9Za+T/UnbbHqlyJfjMf7/HELHmQYemDpCr6n1sIYMjsWIJI/P6ZsQiG/8V
 iDZQGIM8mfUC+PMzxsYAQZQB3nm6noZfnWlAcuChDCmgk2ZxdXSdZlHneiLLiYlb
 yZPOyTysA0H2iFgRGfXMI4Oz6vegr6xAcZ2c9mkc8lM42yKHQNpPa0PqEY+EzVV8
 0iaMT3LKWQRdjzTq6E4I5wb74KQn/t1TbTzM5wznOQ6GySRhPvnXVLOuYyUf5d+0
 PwtnfKyx2C5UtOn47Xuujp5FClP8NI8Se5uq6Myei5OtYAvrQtOFxiJAixLx8nCb
 ca/migenYr+R5zYn5g3o6oo2BUJfF3Y1Q8nazz602JRu42aZzVFu2GNB062YjleK
 w7SfIZNTh0picxSmoehSOQMVaiGY/C/ow7Xa+bLaCITQC3s8HY73m3gynaVOB23X
 2umrC3HkTnH2ymqvDC6O/5QG7IUlSfjbWzN0TdmPfV5KeM7BmBvP4vxqxRYyTY7b
 7UhFg820fZKZu4Ul740a2+HBNw73T8fc4xbZVJ6glJo3AdWQD5s=
 =YD+W
 -----END PGP SIGNATURE-----

Merge tag 'kvm-s390-pci-5.20' into kernelorgnext

KVM: s390/pci: enable zPCI for interpretive execution

Add the necessary code in s390 base, pci and KVM to enable interpretion
of PCI pasthru.
This commit is contained in:
Christian Borntraeger 2022-07-11 11:28:57 +02:00
parent 4b88b1a518 4ac34b94a5
commit d41b5e0176
32 changed files with 1278 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
Documentation/virt/kvm/api.rst
View File

@ -5955,6 +5955,52 @@ KVM_PV_DUMP_CPU
Provides encrypted dump data like register values.
The length of the returned data is provided by uv_info.guest_cpu_stor_len.
4.137 KVM_S390_ZPCI_OP
--------------------
:Capability: KVM_CAP_S390_ZPCI_OP
:Architectures: s390
:Type: vm ioctl
:Parameters: struct kvm_s390_zpci_op (in)
:Returns: 0 on success, <0 on error
Used to manage hardware-assisted virtualization features for zPCI devices.
Parameters are specified via the following structure::
struct kvm_s390_zpci_op {
/* in */
__u32 fh; /* target device */
__u8 op; /* operation to perform */
__u8 pad[3];
union {
/* for KVM_S390_ZPCIOP_REG_AEN */
struct {
__u64 ibv; /* Guest addr of interrupt bit vector */
__u64 sb; /* Guest addr of summary bit */
__u32 flags;
__u32 noi; /* Number of interrupts */
__u8 isc; /* Guest interrupt subclass */
__u8 sbo; /* Offset of guest summary bit vector */
__u16 pad;
} reg_aen;
__u64 reserved[8];
} u;
};
The type of operation is specified in the "op" field.
KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event
notification interpretation, which will allow firmware delivery of adapter
events directly to the vm, with KVM providing a backup delivery mechanism;
KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of
adapter event notifications.
The target zPCI function must also be specified via the "fh" field. For the
KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware
delivery must be provided via the "reg_aen" struct.
The "pad" and "reserved" fields may be used for future extensions and should be
set to 0s by userspace.
5. The kvm_run structure
========================

1
MAINTAINERS
View File

@ -17453,6 +17453,7 @@ M: Eric Farman <farman@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: kvm@vger.kernel.org
S: Supported
F: arch/s390/kvm/pci*
F: drivers/vfio/pci/vfio_pci_zdev.c
F: include/uapi/linux/vfio_zdev.h

7
arch/s390/include/asm/airq.h
View File

@ -12,10 +12,11 @@
#include <linux/bit_spinlock.h>
#include <linux/dma-mapping.h>
#include <asm/tpi.h>
struct airq_struct {
struct hlist_node list; /* Handler queueing. */
void (*handler)(struct airq_struct *airq, bool floating);
void (*handler)(struct airq_struct *airq, struct tpi_info *tpi_info);
u8 *lsi_ptr; /* Local-Summary-Indicator pointer */
u8 lsi_mask; /* Local-Summary-Indicator mask */
u8 isc; /* Interrupt-subclass */
@ -46,8 +47,10 @@ struct airq_iv {
#define AIRQ_IV_PTR 4 /* Allocate the ptr array */
#define AIRQ_IV_DATA 8 /* Allocate the data array */
#define AIRQ_IV_CACHELINE 16 /* Cacheline alignment for the vector */
#define AIRQ_IV_GUESTVEC 32 /* Vector is a pinned guest page */
struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags,
unsigned long *vec);
void airq_iv_release(struct airq_iv *iv);
unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num);
void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num);

23
arch/s390/include/asm/kvm_host.h
View File

@ -19,6 +19,7 @@
#include <linux/kvm.h>
#include <linux/seqlock.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <asm/debug.h>
#include <asm/cpu.h>
#include <asm/fpu/api.h>
@ -254,7 +255,10 @@ struct kvm_s390_sie_block {
#define ECB2_IEP 0x20
#define ECB2_PFMFI 0x08
#define ECB2_ESCA 0x04
#define ECB2_ZPCI_LSI 0x02
__u8 ecb2; /* 0x0062 */
#define ECB3_AISI 0x20
#define ECB3_AISII 0x10
#define ECB3_DEA 0x08
#define ECB3_AES 0x04
#define ECB3_RI 0x01
@ -759,6 +763,7 @@ struct kvm_vm_stat {
u64 inject_pfault_done;
u64 inject_service_signal;
u64 inject_virtio;
u64 aen_forward;
};
struct kvm_arch_memory_slot {
@ -940,6 +945,7 @@ struct kvm_arch{
int use_cmma;
int use_pfmfi;
int use_skf;
int use_zpci_interp;
int user_cpu_state_ctrl;
int user_sigp;
int user_stsi;
@ -963,6 +969,8 @@ struct kvm_arch{
DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS);
struct kvm_s390_gisa_interrupt gisa_int;
struct kvm_s390_pv pv;
struct list_head kzdev_list;
spinlock_t kzdev_list_lock;
};
#define KVM_HVA_ERR_BAD (-1UL)
@ -1013,4 +1021,19 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
#define __KVM_HAVE_ARCH_VM_FREE
void kvm_arch_free_vm(struct kvm *kvm);
#ifdef CONFIG_VFIO_PCI_ZDEV_KVM
int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm);
void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev);
#else
static inline int kvm_s390_pci_register_kvm(struct zpci_dev *dev,
struct kvm *kvm)
{
return -EPERM;
}
static inline void kvm_s390_pci_unregister_kvm(struct zpci_dev *dev) {}
#endif
#endif

11
arch/s390/include/asm/pci.h
View File

@ -9,6 +9,7 @@
#include <asm-generic/pci.h>
#include <asm/pci_clp.h>
#include <asm/pci_debug.h>
#include <asm/pci_insn.h>
#include <asm/sclp.h>
#define PCIBIOS_MIN_IO 0x1000
@ -97,6 +98,7 @@ struct zpci_bar_struct {
};
struct s390_domain;
struct kvm_zdev;
#define ZPCI_FUNCTIONS_PER_BUS 256
struct zpci_bus {
@ -123,11 +125,14 @@ struct zpci_dev {
enum zpci_state state;
u32 fid; /* function ID, used by sclp */
u32 fh; /* function handle, used by insn's */
u32 gisa; /* GISA designation for passthrough */
u16 vfn; /* virtual function number */
u16 pchid; /* physical channel ID */
u16 maxstbl; /* Maximum store block size */
u8 pfgid; /* function group ID */
u8 pft; /* pci function type */
u8 port;
u8 dtsm; /* Supported DT mask */
u8 rid_available : 1;
u8 has_hp_slot : 1;
u8 has_resources : 1;
@ -186,7 +191,10 @@ struct zpci_dev {
struct dentry *debugfs_dev;
/* IOMMU and passthrough */
struct s390_domain *s390_domain; /* s390 IOMMU domain data */
struct kvm_zdev *kzdev;
struct mutex kzdev_lock;
};
static inline bool zdev_enabled(struct zpci_dev *zdev)
@ -198,6 +206,9 @@ extern const struct attribute_group *zpci_attr_groups[];
extern unsigned int s390_pci_force_floating __initdata;
extern unsigned int s390_pci_no_rid;
extern union zpci_sic_iib *zpci_aipb;
extern struct airq_iv *zpci_aif_sbv;
/* -----------------------------------------------------------------------------
Prototypes
----------------------------------------------------------------------------- */

9
arch/s390/include/asm/pci_clp.h
View File

@ -153,9 +153,11 @@ struct clp_rsp_query_pci_grp {
u8 : 6;
u8 frame : 1;
u8 refresh : 1; /* TLB refresh mode */
u16 reserved2;
u16 : 3;
u16 maxstbl : 13; /* Maximum store block size */
u16 mui;
u16 : 16;
u8 dtsm; /* Supported DT mask */
u8 reserved3;
u16 maxfaal;
u16 : 4;
u16 dnoi : 12;
@ -173,7 +175,8 @@ struct clp_req_set_pci {
u16 reserved2;
u8 oc; /* operation controls */
u8 ndas; /* number of dma spaces */
u64 reserved3;
u32 reserved3;
u32 gisa; /* GISA designation */
} __packed;
/* Set PCI function response */

29
arch/s390/include/asm/pci_insn.h
View File

@ -98,6 +98,15 @@ struct zpci_fib {
u32 gd;
} __packed __aligned(8);
/* Set Interruption Controls Operation Controls */
#define SIC_IRQ_MODE_ALL 0
#define SIC_IRQ_MODE_SINGLE 1
#define SIC_SET_AENI_CONTROLS 2
#define SIC_IRQ_MODE_DIRECT 4
#define SIC_IRQ_MODE_D_ALL 16
#define SIC_IRQ_MODE_D_SINGLE 17
#define SIC_IRQ_MODE_SET_CPU 18
/* directed interruption information block */
struct zpci_diib {
u32 : 1;
@ -119,9 +128,20 @@ struct zpci_cdiib {
u64 : 64;
} __packed __aligned(8);
/* adapter interruption parameters block */
struct zpci_aipb {
u64 faisb;
u64 gait;
u16 : 13;
u16 afi : 3;
u32 : 32;
u16 faal;
} __packed __aligned(8);
union zpci_sic_iib {
struct zpci_diib diib;
struct zpci_cdiib cdiib;
struct zpci_aipb aipb;
};
DECLARE_STATIC_KEY_FALSE(have_mio);
@ -134,13 +154,6 @@ int __zpci_store(u64 data, u64 req, u64 offset);
int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len);
int __zpci_store_block(const u64 *data, u64 req, u64 offset);
void zpci_barrier(void);
int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib);
static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc)
{
union zpci_sic_iib iib = {{0}};
return __zpci_set_irq_ctrl(ctl, isc, &iib);
}
int zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib);
#endif

4
arch/s390/include/asm/sclp.h
View File

@ -88,6 +88,10 @@ struct sclp_info {
unsigned char has_sipl : 1;
unsigned char has_dirq : 1;
unsigned char has_iplcc : 1;
unsigned char has_zpci_lsi : 1;
unsigned char has_aisii : 1;
unsigned char has_aeni : 1;
unsigned char has_aisi : 1;
unsigned int ibc;
unsigned int mtid;
unsigned int mtid_cp;

13
arch/s390/include/asm/tpi.h
View File

@ -19,6 +19,19 @@ struct tpi_info {
u32 :12;
} __packed __aligned(4);
/* I/O-Interruption Code as stored by TPI for an Adapter I/O */
struct tpi_adapter_info {
u32 aism:8;
u32 :22;
u32 error:1;
u32 forward:1;
u32 reserved;
u32 adapter_IO:1;
u32 directed_irq:1;
u32 isc:3;
u32 :27;
} __packed __aligned(4);
#endif /* __ASSEMBLY__ */
#endif /* _ASM_S390_TPI_H */

1
arch/s390/kvm/Makefile
View File

@ -10,4 +10,5 @@ ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o
kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o
kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o
obj-$(CONFIG_KVM) += kvm.o

96
arch/s390/kvm/interrupt.c
View File

@ -28,9 +28,11 @@
#include <asm/switch_to.h>
#include <asm/nmi.h>
#include <asm/airq.h>
#include <asm/tpi.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "trace-s390.h"
#include "pci.h"
#define PFAULT_INIT 0x0600
#define PFAULT_DONE 0x0680
@ -3311,10 +3313,87 @@ out:
}
EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister);
static void gib_alert_irq_handler(struct airq_struct *airq, bool floating)
static void aen_host_forward(unsigned long si)
{
struct kvm_s390_gisa_interrupt *gi;
struct zpci_gaite *gaite;
struct kvm *kvm;
gaite = (struct zpci_gaite *)aift->gait +
(si * sizeof(struct zpci_gaite));
if (gaite->count == 0)
return;
if (gaite->aisb != 0)
set_bit_inv(gaite->aisbo, (unsigned long *)gaite->aisb);
kvm = kvm_s390_pci_si_to_kvm(aift, si);
if (!kvm)
return;
gi = &kvm->arch.gisa_int;
if (!(gi->origin->g1.simm & AIS_MODE_MASK(gaite->gisc)) ||
!(gi->origin->g1.nimm & AIS_MODE_MASK(gaite->gisc))) {
gisa_set_ipm_gisc(gi->origin, gaite->gisc);
if (hrtimer_active(&gi->timer))
hrtimer_cancel(&gi->timer);
hrtimer_start(&gi->timer, 0, HRTIMER_MODE_REL);
kvm->stat.aen_forward++;
}
}
static void aen_process_gait(u8 isc)
{
bool found = false, first = true;
union zpci_sic_iib iib = {{0}};
unsigned long si, flags;
spin_lock_irqsave(&aift->gait_lock, flags);
if (!aift->gait) {
spin_unlock_irqrestore(&aift->gait_lock, flags);
return;
}
for (si = 0;;) {
/* Scan adapter summary indicator bit vector */
si = airq_iv_scan(aift->sbv, si, airq_iv_end(aift->sbv));
if (si == -1UL) {
if (first || found) {
/* Re-enable interrupts. */
zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, isc,
&iib);
first = found = false;
} else {
/* Interrupts on and all bits processed */
break;
}
found = false;
si = 0;
/* Scan again after re-enabling interrupts */
continue;
}
found = true;
aen_host_forward(si);
}
spin_unlock_irqrestore(&aift->gait_lock, flags);
}
static void gib_alert_irq_handler(struct airq_struct *airq,
struct tpi_info *tpi_info)
{
struct tpi_adapter_info *info = (struct tpi_adapter_info *)tpi_info;
inc_irq_stat(IRQIO_GAL);
process_gib_alert_list();
if ((info->forward || info->error) &&
IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
aen_process_gait(info->isc);
if (info->aism != 0)
process_gib_alert_list();
} else {
process_gib_alert_list();
}
}
static struct airq_struct gib_alert_irq = {
@ -3326,6 +3405,11 @@ void kvm_s390_gib_destroy(void)
{
if (!gib)
return;
if (kvm_s390_pci_interp_allowed() && aift) {
mutex_lock(&aift->aift_lock);
kvm_s390_pci_aen_exit();
mutex_unlock(&aift->aift_lock);
}
chsc_sgib(0);
unregister_adapter_interrupt(&gib_alert_irq);
free_page((unsigned long)gib);
@ -3363,6 +3447,14 @@ int kvm_s390_gib_init(u8 nisc)
goto out_unreg_gal;
}
if (kvm_s390_pci_interp_allowed()) {
if (kvm_s390_pci_aen_init(nisc)) {
pr_err("Initializing AEN for PCI failed\n");
rc = -EIO;
goto out_unreg_gal;
}
}
KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc);
goto out;

83
arch/s390/kvm/kvm-s390.c
View File

@ -47,6 +47,7 @@
#include <asm/fpu/api.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "pci.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
@ -63,7 +64,8 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
STATS_DESC_COUNTER(VM, inject_float_mchk),
STATS_DESC_COUNTER(VM, inject_pfault_done),
STATS_DESC_COUNTER(VM, inject_service_signal),
STATS_DESC_COUNTER(VM, inject_virtio)
STATS_DESC_COUNTER(VM, inject_virtio),
STATS_DESC_COUNTER(VM, aen_forward)
};
const struct kvm_stats_header kvm_vm_stats_header = {
@ -502,6 +504,14 @@ int kvm_arch_init(void *opaque)
goto out;
}
if (kvm_s390_pci_interp_allowed()) {
rc = kvm_s390_pci_init();
if (rc) {
pr_err("Unable to allocate AIFT for PCI\n");
goto out;
}
}
rc = kvm_s390_gib_init(GAL_ISC);
if (rc)
goto out;
@ -516,6 +526,8 @@ out:
void kvm_arch_exit(void)
{
kvm_s390_gib_destroy();
if (kvm_s390_pci_interp_allowed())
kvm_s390_pci_exit();
debug_unregister(kvm_s390_dbf);
debug_unregister(kvm_s390_dbf_uv);
}
@ -626,6 +638,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
}
break;
}
case KVM_CAP_S390_ZPCI_OP:
r = kvm_s390_pci_interp_allowed();
break;
default:
r = 0;
}
@ -1039,6 +1054,42 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
return 0;
}
static void kvm_s390_vcpu_pci_setup(struct kvm_vcpu *vcpu)
{
/* Only set the ECB bits after guest requests zPCI interpretation */
if (!vcpu->kvm->arch.use_zpci_interp)
return;
vcpu->arch.sie_block->ecb2 |= ECB2_ZPCI_LSI;
vcpu->arch.sie_block->ecb3 |= ECB3_AISII + ECB3_AISI;
}
void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
unsigned long i;
lockdep_assert_held(&kvm->lock);
if (!kvm_s390_pci_interp_allowed())
return;
/*
* If host is configured for PCI and the necessary facilities are
* available, turn on interpretation for the life of this guest
*/
kvm->arch.use_zpci_interp = 1;
kvm_s390_vcpu_block_all(kvm);
kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_s390_vcpu_pci_setup(vcpu);
kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu);
}
kvm_s390_vcpu_unblock_all(kvm);
}
static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
{
unsigned long cx;
@ -2772,6 +2823,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
break;
}
case KVM_S390_ZPCI_OP: {
struct kvm_s390_zpci_op args;
r = -EINVAL;
if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
break;
if (copy_from_user(&args, argp, sizeof(args))) {
r = -EFAULT;
break;
}
r = kvm_s390_pci_zpci_op(kvm, &args);
break;
}
default:
r = -ENOTTY;
}
@ -2933,6 +2997,14 @@ static void sca_dispose(struct kvm *kvm)
kvm->arch.sca = NULL;
}
void kvm_arch_free_vm(struct kvm *kvm)
{
if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
kvm_s390_pci_clear_list(kvm);
__kvm_arch_free_vm(kvm);
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
gfp_t alloc_flags = GFP_KERNEL_ACCOUNT;
@ -3015,6 +3087,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm_s390_crypto_init(kvm);
if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
mutex_lock(&kvm->lock);
kvm_s390_pci_init_list(kvm);
kvm_s390_vcpu_pci_enable_interp(kvm);
mutex_unlock(&kvm->lock);
}
mutex_init(&kvm->arch.float_int.ais_lock);
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
@ -3513,6 +3592,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
kvm_s390_vcpu_crypto_setup(vcpu);
kvm_s390_vcpu_pci_setup(vcpu);
mutex_lock(&vcpu->kvm->lock);
if (kvm_s390_pv_is_protected(vcpu->kvm)) {
rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc);

10
arch/s390/kvm/kvm-s390.h
View File

@ -512,6 +512,16 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
*/
void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm);
/**
* kvm_s390_vcpu_pci_enable_interp
*
* Set the associated PCI attributes for each vcpu to allow for zPCI Load/Store
* interpretation as well as adapter interruption forwarding.
*
* @kvm: the KVM guest
*/
void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm);
/**
* diag9c_forwarding_hz
*

690
arch/s390/kvm/pci.c Normal file
View File

@ -0,0 +1,690 @@
// SPDX-License-Identifier: GPL-2.0
/*
* s390 kvm PCI passthrough support
*
* Copyright IBM Corp. 2022
*
* Author(s): Matthew Rosato <mjrosato@linux.ibm.com>
*/
#include <linux/kvm_host.h>
#include <linux/pci.h>
#include <asm/pci.h>
#include <asm/pci_insn.h>
#include <asm/pci_io.h>
#include <asm/sclp.h>
#include "pci.h"
#include "kvm-s390.h"
struct zpci_aift *aift;
static inline int __set_irq_noiib(u16 ctl, u8 isc)
{
union zpci_sic_iib iib = {{0}};
return zpci_set_irq_ctrl(ctl, isc, &iib);
}
void kvm_s390_pci_aen_exit(void)
{
unsigned long flags;
struct kvm_zdev **gait_kzdev;
lockdep_assert_held(&aift->aift_lock);
/*
* Contents of the aipb remain registered for the life of the host
* kernel, the information preserved in zpci_aipb and zpci_aif_sbv
* in case we insert the KVM module again later. Clear the AIFT
* information and free anything not registered with underlying
* firmware.
*/
spin_lock_irqsave(&aift->gait_lock, flags);
gait_kzdev = aift->kzdev;
aift->gait = NULL;
aift->sbv = NULL;
aift->kzdev = NULL;
spin_unlock_irqrestore(&aift->gait_lock, flags);
kfree(gait_kzdev);
}
static int zpci_setup_aipb(u8 nisc)
{
struct page *page;
int size, rc;
zpci_aipb = kzalloc(sizeof(union zpci_sic_iib), GFP_KERNEL);
if (!zpci_aipb)
return -ENOMEM;
aift->sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, 0);
if (!aift->sbv) {
rc = -ENOMEM;
goto free_aipb;
}
zpci_aif_sbv = aift->sbv;
size = get_order(PAGE_ALIGN(ZPCI_NR_DEVICES *
sizeof(struct zpci_gaite)));
page = alloc_pages(GFP_KERNEL | __GFP_ZERO, size);
if (!page) {
rc = -ENOMEM;
goto free_sbv;
}
aift->gait = (struct zpci_gaite *)page_to_phys(page);
zpci_aipb->aipb.faisb = virt_to_phys(aift->sbv->vector);
zpci_aipb->aipb.gait = virt_to_phys(aift->gait);
zpci_aipb->aipb.afi = nisc;
zpci_aipb->aipb.faal = ZPCI_NR_DEVICES;
/* Setup Adapter Event Notification Interpretation */
if (zpci_set_irq_ctrl(SIC_SET_AENI_CONTROLS, 0, zpci_aipb)) {
rc = -EIO;
goto free_gait;
}
return 0;
free_gait:
free_pages((unsigned long)aift->gait, size);
free_sbv:
airq_iv_release(aift->sbv);
zpci_aif_sbv = NULL;
free_aipb:
kfree(zpci_aipb);
zpci_aipb = NULL;
return rc;
}
static int zpci_reset_aipb(u8 nisc)
{
/*
* AEN registration can only happen once per system boot. If
* an aipb already exists then AEN was already registered and
* we can re-use the aipb contents. This can only happen if
* the KVM module was removed and re-inserted. However, we must
* ensure that the same forwarding ISC is used as this is assigned
* during KVM module load.
*/
if (zpci_aipb->aipb.afi != nisc)
return -EINVAL;
aift->sbv = zpci_aif_sbv;
aift->gait = (struct zpci_gaite *)zpci_aipb->aipb.gait;
return 0;
}
int kvm_s390_pci_aen_init(u8 nisc)
{
int rc = 0;
/* If already enabled for AEN, bail out now */
if (aift->gait || aift->sbv)
return -EPERM;
mutex_lock(&aift->aift_lock);
aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev),
GFP_KERNEL);
if (!aift->kzdev) {
rc = -ENOMEM;
goto unlock;
}
if (!zpci_aipb)
rc = zpci_setup_aipb(nisc);
else
rc = zpci_reset_aipb(nisc);
if (rc)
goto free_zdev;
/* Enable floating IRQs */
if (__set_irq_noiib(SIC_IRQ_MODE_SINGLE, nisc)) {
rc = -EIO;
kvm_s390_pci_aen_exit();
}
goto unlock;
free_zdev:
kfree(aift->kzdev);
unlock:
mutex_unlock(&aift->aift_lock);
return rc;
}
/* Modify PCI: Register floating adapter interruption forwarding */
static int kvm_zpci_set_airq(struct zpci_dev *zdev)
{
u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
struct zpci_fib fib = {};
u8 status;
fib.fmt0.isc = zdev->kzdev->fib.fmt0.isc;
fib.fmt0.sum = 1; /* enable summary notifications */
fib.fmt0.noi = airq_iv_end(zdev->aibv);
fib.fmt0.aibv = virt_to_phys(zdev->aibv->vector);
fib.fmt0.aibvo = 0;
fib.fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8);
fib.fmt0.aisbo = zdev->aisb & 63;
fib.gd = zdev->gisa;
return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
}
/* Modify PCI: Unregister floating adapter interruption forwarding */
static int kvm_zpci_clear_airq(struct zpci_dev *zdev)
{
u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
struct zpci_fib fib = {};
u8 cc, status;
fib.gd = zdev->gisa;
cc = zpci_mod_fc(req, &fib, &status);
if (cc == 3 || (cc == 1 && status == 24))
/* Function already gone or IRQs already deregistered. */
cc = 0;
return cc ? -EIO : 0;
}
static inline void unaccount_mem(unsigned long nr_pages)
{
struct user_struct *user = get_uid(current_user());
if (user)
atomic_long_sub(nr_pages, &user->locked_vm);
if (current->mm)
atomic64_sub(nr_pages, &current->mm->pinned_vm);
}
static inline int account_mem(unsigned long nr_pages)
{
struct user_struct *user = get_uid(current_user());
unsigned long page_limit, cur_pages, new_pages;
page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
do {
cur_pages = atomic_long_read(&user->locked_vm);
new_pages = cur_pages + nr_pages;
if (new_pages > page_limit)
return -ENOMEM;
} while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
new_pages) != cur_pages);
atomic64_add(nr_pages, &current->mm->pinned_vm);
return 0;
}
static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
bool assist)
{
struct page *pages[1], *aibv_page, *aisb_page = NULL;
unsigned int msi_vecs, idx;
struct zpci_gaite *gaite;
unsigned long hva, bit;
struct kvm *kvm;
phys_addr_t gaddr;
int rc = 0, gisc, npages, pcount = 0;
/*
* Interrupt forwarding is only applicable if the device is already
* enabled for interpretation
*/
if (zdev->gisa == 0)
return -EINVAL;
kvm = zdev->kzdev->kvm;
msi_vecs = min_t(unsigned int, fib->fmt0.noi, zdev->max_msi);
/* Get the associated forwarding ISC - if invalid, return the error */
gisc = kvm_s390_gisc_register(kvm, fib->fmt0.isc);
if (gisc < 0)
return gisc;
/* Replace AIBV address */
idx = srcu_read_lock(&kvm->srcu);
hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aibv));
npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, pages);
srcu_read_unlock(&kvm->srcu, idx);
if (npages < 1) {
rc = -EIO;
goto out;
}
aibv_page = pages[0];
pcount++;
gaddr = page_to_phys(aibv_page) + (fib->fmt0.aibv & ~PAGE_MASK);
fib->fmt0.aibv = gaddr;
/* Pin the guest AISB if one was specified */
if (fib->fmt0.sum == 1) {
idx = srcu_read_lock(&kvm->srcu);
hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aisb));
npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM,
pages);
srcu_read_unlock(&kvm->srcu, idx);
if (npages < 1) {
rc = -EIO;
goto unpin1;
}
aisb_page = pages[0];
pcount++;
}
/* Account for pinned pages, roll back on failure */
if (account_mem(pcount))
goto unpin2;
/* AISB must be allocated before we can fill in GAITE */
mutex_lock(&aift->aift_lock);
bit = airq_iv_alloc_bit(aift->sbv);
if (bit == -1UL)
goto unlock;
zdev->aisb = bit; /* store the summary bit number */
zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA |
AIRQ_IV_BITLOCK |
AIRQ_IV_GUESTVEC,
phys_to_virt(fib->fmt0.aibv));
spin_lock_irq(&aift->gait_lock);
gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb *
sizeof(struct zpci_gaite));
/* If assist not requested, host will get all alerts */
if (assist)
gaite->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa);
else
gaite->gisa = 0;
gaite->gisc = fib->fmt0.isc;
gaite->count++;
gaite->aisbo = fib->fmt0.aisbo;
gaite->aisb = virt_to_phys(page_address(aisb_page) + (fib->fmt0.aisb &
~PAGE_MASK));
aift->kzdev[zdev->aisb] = zdev->kzdev;
spin_unlock_irq(&aift->gait_lock);
/* Update guest FIB for re-issue */
fib->fmt0.aisbo = zdev->aisb & 63;
fib->fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8);
fib->fmt0.isc = gisc;
/* Save some guest fib values in the host for later use */
zdev->kzdev->fib.fmt0.isc = fib->fmt0.isc;
zdev->kzdev->fib.fmt0.aibv = fib->fmt0.aibv;
mutex_unlock(&aift->aift_lock);
/* Issue the clp to setup the irq now */
rc = kvm_zpci_set_airq(zdev);
return rc;
unlock:
mutex_unlock(&aift->aift_lock);
unpin2:
if (fib->fmt0.sum == 1)
unpin_user_page(aisb_page);
unpin1:
unpin_user_page(aibv_page);
out:
return rc;
}
static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force)
{
struct kvm_zdev *kzdev = zdev->kzdev;
struct zpci_gaite *gaite;
struct page *vpage = NULL, *spage = NULL;
int rc, pcount = 0;
u8 isc;
if (zdev->gisa == 0)
return -EINVAL;
mutex_lock(&aift->aift_lock);
/*
* If the clear fails due to an error, leave now unless we know this
* device is about to go away (force) -- In that case clear the GAITE
* regardless.
*/
rc = kvm_zpci_clear_airq(zdev);
if (rc && !force)
goto out;
if (zdev->kzdev->fib.fmt0.aibv == 0)
goto out;
spin_lock_irq(&aift->gait_lock);
gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb *
sizeof(struct zpci_gaite));
isc = gaite->gisc;
gaite->count--;
if (gaite->count == 0) {
/* Release guest AIBV and AISB */
vpage = phys_to_page(kzdev->fib.fmt0.aibv);
if (gaite->aisb != 0)
spage = phys_to_page(gaite->aisb);
/* Clear the GAIT entry */
gaite->aisb = 0;
gaite->gisc = 0;
gaite->aisbo = 0;
gaite->gisa = 0;
aift->kzdev[zdev->aisb] = 0;
/* Clear zdev info */
airq_iv_free_bit(aift->sbv, zdev->aisb);
airq_iv_release(zdev->aibv);
zdev->aisb = 0;
zdev->aibv = NULL;
}
spin_unlock_irq(&aift->gait_lock);
kvm_s390_gisc_unregister(kzdev->kvm, isc);
kzdev->fib.fmt0.isc = 0;
kzdev->fib.fmt0.aibv = 0;
if (vpage) {
unpin_user_page(vpage);
pcount++;
}
if (spage) {
unpin_user_page(spage);
pcount++;
}
if (pcount > 0)
unaccount_mem(pcount);
out:
mutex_unlock(&aift->aift_lock);
return rc;
}
static int kvm_s390_pci_dev_open(struct zpci_dev *zdev)
{
struct kvm_zdev *kzdev;
kzdev = kzalloc(sizeof(struct kvm_zdev), GFP_KERNEL);
if (!kzdev)
return -ENOMEM;
kzdev->zdev = zdev;
zdev->kzdev = kzdev;
return 0;
}
static void kvm_s390_pci_dev_release(struct zpci_dev *zdev)
{
struct kvm_zdev *kzdev;
kzdev = zdev->kzdev;
WARN_ON(kzdev->zdev != zdev);
zdev->kzdev = NULL;
kfree(kzdev);
}
/*
* Register device with the specified KVM. If interpetation facilities are
* available, enable them and let userspace indicate whether or not they will
* be used (specify SHM bit to disable).
*/
int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm)
{
int rc;
if (!zdev)
return -EINVAL;
mutex_lock(&zdev->kzdev_lock);
if (zdev->kzdev || zdev->gisa != 0 || !kvm) {
mutex_unlock(&zdev->kzdev_lock);
return -EINVAL;
}
kvm_get_kvm(kvm);
mutex_lock(&kvm->lock);
rc = kvm_s390_pci_dev_open(zdev);
if (rc)
goto err;
/*
* If interpretation facilities aren't available, add the device to
* the kzdev list but don't enable for interpretation.
*/
if (!kvm_s390_pci_interp_allowed())
goto out;
/*
* If this is the first request to use an interpreted device, make the
* necessary vcpu changes
*/
if (!kvm->arch.use_zpci_interp)
kvm_s390_vcpu_pci_enable_interp(kvm);
if (zdev_enabled(zdev)) {
rc = zpci_disable_device(zdev);
if (rc)
goto err;
}
/*
* Store information about the identity of the kvm guest allowed to
* access this device via interpretation to be used by host CLP
*/
zdev->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa);
rc = zpci_enable_device(zdev);
if (rc)
goto clear_gisa;
/* Re-register the IOMMU that was already created */
rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
virt_to_phys(zdev->dma_table));
if (rc)
goto clear_gisa;
out:
zdev->kzdev->kvm = kvm;
spin_lock(&kvm->arch.kzdev_list_lock);
list_add_tail(&zdev->kzdev->entry, &kvm->arch.kzdev_list);
spin_unlock(&kvm->arch.kzdev_list_lock);
mutex_unlock(&kvm->lock);
mutex_unlock(&zdev->kzdev_lock);
return 0;
clear_gisa:
zdev->gisa = 0;
err:
if (zdev->kzdev)
kvm_s390_pci_dev_release(zdev);
mutex_unlock(&kvm->lock);
mutex_unlock(&zdev->kzdev_lock);
kvm_put_kvm(kvm);
return rc;
}
EXPORT_SYMBOL_GPL(kvm_s390_pci_register_kvm);
void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev)
{
struct kvm *kvm;
if (!zdev)
return;
mutex_lock(&zdev->kzdev_lock);
if (WARN_ON(!zdev->kzdev)) {
mutex_unlock(&zdev->kzdev_lock);
return;
}
kvm = zdev->kzdev->kvm;
mutex_lock(&kvm->lock);
/*
* A 0 gisa means interpretation was never enabled, just remove the
* device from the list.
*/
if (zdev->gisa == 0)
goto out;
/* Forwarding must be turned off before interpretation */
if (zdev->kzdev->fib.fmt0.aibv != 0)
kvm_s390_pci_aif_disable(zdev, true);
/* Remove the host CLP guest designation */
zdev->gisa = 0;
if (zdev_enabled(zdev)) {
if (zpci_disable_device(zdev))
goto out;
}
if (zpci_enable_device(zdev))
goto out;
/* Re-register the IOMMU that was already created */
zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
virt_to_phys(zdev->dma_table));
out:
spin_lock(&kvm->arch.kzdev_list_lock);
list_del(&zdev->kzdev->entry);
spin_unlock(&kvm->arch.kzdev_list_lock);
kvm_s390_pci_dev_release(zdev);
mutex_unlock(&kvm->lock);
mutex_unlock(&zdev->kzdev_lock);
kvm_put_kvm(kvm);
}
EXPORT_SYMBOL_GPL(kvm_s390_pci_unregister_kvm);
void kvm_s390_pci_init_list(struct kvm *kvm)
{
spin_lock_init(&kvm->arch.kzdev_list_lock);
INIT_LIST_HEAD(&kvm->arch.kzdev_list);
}
void kvm_s390_pci_clear_list(struct kvm *kvm)
{
/*
* This list should already be empty, either via vfio device closures
* or kvm fd cleanup.
*/
spin_lock(&kvm->arch.kzdev_list_lock);
WARN_ON_ONCE(!list_empty(&kvm->arch.kzdev_list));
spin_unlock(&kvm->arch.kzdev_list_lock);
}
static struct zpci_dev *get_zdev_from_kvm_by_fh(struct kvm *kvm, u32 fh)
{
struct zpci_dev *zdev = NULL;
struct kvm_zdev *kzdev;
spin_lock(&kvm->arch.kzdev_list_lock);
list_for_each_entry(kzdev, &kvm->arch.kzdev_list, entry) {
if (kzdev->zdev->fh == fh) {
zdev = kzdev->zdev;
break;
}
}
spin_unlock(&kvm->arch.kzdev_list_lock);
return zdev;
}
static int kvm_s390_pci_zpci_reg_aen(struct zpci_dev *zdev,
struct kvm_s390_zpci_op *args)
{
struct zpci_fib fib = {};
bool hostflag;
fib.fmt0.aibv = args->u.reg_aen.ibv;
fib.fmt0.isc = args->u.reg_aen.isc;
fib.fmt0.noi = args->u.reg_aen.noi;
if (args->u.reg_aen.sb != 0) {
fib.fmt0.aisb = args->u.reg_aen.sb;
fib.fmt0.aisbo = args->u.reg_aen.sbo;
fib.fmt0.sum = 1;
} else {
fib.fmt0.aisb = 0;
fib.fmt0.aisbo = 0;
fib.fmt0.sum = 0;
}
hostflag = !(args->u.reg_aen.flags & KVM_S390_ZPCIOP_REGAEN_HOST);
return kvm_s390_pci_aif_enable(zdev, &fib, hostflag);
}
int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args)
{
struct kvm_zdev *kzdev;
struct zpci_dev *zdev;
int r;
zdev = get_zdev_from_kvm_by_fh(kvm, args->fh);
if (!zdev)
return -ENODEV;
mutex_lock(&zdev->kzdev_lock);
mutex_lock(&kvm->lock);
kzdev = zdev->kzdev;
if (!kzdev) {
r = -ENODEV;
goto out;
}
if (kzdev->kvm != kvm) {
r = -EPERM;
goto out;
}
switch (args->op) {
case KVM_S390_ZPCIOP_REG_AEN:
/* Fail on unknown flags */
if (args->u.reg_aen.flags & ~KVM_S390_ZPCIOP_REGAEN_HOST) {
r = -EINVAL;
break;
}
r = kvm_s390_pci_zpci_reg_aen(zdev, args);
break;
case KVM_S390_ZPCIOP_DEREG_AEN:
r = kvm_s390_pci_aif_disable(zdev, false);
break;
default:
r = -EINVAL;
}
out:
mutex_unlock(&kvm->lock);
mutex_unlock(&zdev->kzdev_lock);
return r;
}
int kvm_s390_pci_init(void)
{
aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL);
if (!aift)
return -ENOMEM;
spin_lock_init(&aift->gait_lock);
mutex_init(&aift->aift_lock);
return 0;
}
void kvm_s390_pci_exit(void)
{
mutex_destroy(&aift->aift_lock);
kfree(aift);
}

88
arch/s390/kvm/pci.h Normal file
View File

@ -0,0 +1,88 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* s390 kvm PCI passthrough support
*
* Copyright IBM Corp. 2022
*
* Author(s): Matthew Rosato <mjrosato@linux.ibm.com>
*/
#ifndef __KVM_S390_PCI_H
#define __KVM_S390_PCI_H
#include <linux/kvm_host.h>
#include <linux/pci.h>
#include <linux/mutex.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/airq.h>
#include <asm/cpu.h>
struct kvm_zdev {
struct zpci_dev *zdev;
struct kvm *kvm;
struct zpci_fib fib;
struct list_head entry;
};
struct zpci_gaite {
u32 gisa;
u8 gisc;
u8 count;
u8 reserved;
u8 aisbo;
u64 aisb;
};
struct zpci_aift {
struct zpci_gaite *gait;
struct airq_iv *sbv;
struct kvm_zdev **kzdev;
spinlock_t gait_lock; /* Protects the gait, used during AEN forward */
struct mutex aift_lock; /* Protects the other structures in aift */
};
extern struct zpci_aift *aift;
static inline struct kvm *kvm_s390_pci_si_to_kvm(struct zpci_aift *aift,
unsigned long si)
{
if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || aift->kzdev == 0 ||
aift->kzdev[si] == 0)
return 0;
return aift->kzdev[si]->kvm;
};
int kvm_s390_pci_aen_init(u8 nisc);
void kvm_s390_pci_aen_exit(void);
void kvm_s390_pci_init_list(struct kvm *kvm);
void kvm_s390_pci_clear_list(struct kvm *kvm);
int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args);
int kvm_s390_pci_init(void);
void kvm_s390_pci_exit(void);
static inline bool kvm_s390_pci_interp_allowed(void)
{
struct cpuid cpu_id;
get_cpu_id(&cpu_id);
switch (cpu_id.machine) {
case 0x2817:
case 0x2818:
case 0x2827:
case 0x2828:
case 0x2964:
case 0x2965:
/* No SHM on certain machines */
return false;
default:
return (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) &&
sclp.has_zpci_lsi && sclp.has_aeni && sclp.has_aisi &&
sclp.has_aisii);
}
}
#endif /* __KVM_S390_PCI_H */

16
arch/s390/pci/pci.c
View File

@ -61,6 +61,12 @@ DEFINE_STATIC_KEY_FALSE(have_mio);
static struct kmem_cache *zdev_fmb_cache;
/* AEN structures that must be preserved over KVM module re-insertion */
union zpci_sic_iib *zpci_aipb;
EXPORT_SYMBOL_GPL(zpci_aipb);
struct airq_iv *zpci_aif_sbv;
EXPORT_SYMBOL_GPL(zpci_aif_sbv);
struct zpci_dev *get_zdev_by_fid(u32 fid)
{
struct zpci_dev *tmp, *zdev = NULL;
@ -120,11 +126,13 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
fib.pba = base;
fib.pal = limit;
fib.iota = iota | ZPCI_IOTA_RTTO_FLAG;
fib.gd = zdev->gisa;
cc = zpci_mod_fc(req, &fib, &status);
if (cc)
zpci_dbg(3, "reg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status);
return cc;
}
EXPORT_SYMBOL_GPL(zpci_register_ioat);
/* Modify PCI: Unregister I/O address translation parameters */
int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
@ -133,6 +141,8 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
struct zpci_fib fib = {0};
u8 cc, status;
fib.gd = zdev->gisa;
cc = zpci_mod_fc(req, &fib, &status);
if (cc)
zpci_dbg(3, "unreg ioat fid:%x, cc:%d, status:%d\n", zdev->fid, cc, status);
@ -160,6 +170,7 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
atomic64_set(&zdev->unmapped_pages, 0);
fib.fmb_addr = virt_to_phys(zdev->fmb);
fib.gd = zdev->gisa;
cc = zpci_mod_fc(req, &fib, &status);
if (cc) {
kmem_cache_free(zdev_fmb_cache, zdev->fmb);
@ -178,6 +189,8 @@ int zpci_fmb_disable_device(struct zpci_dev *zdev)
if (!zdev->fmb)
return -EINVAL;
fib.gd = zdev->gisa;
/* Function measurement is disabled if fmb address is zero */
cc = zpci_mod_fc(req, &fib, &status);
if (cc == 3) /* Function already gone. */
@ -700,6 +713,7 @@ int zpci_enable_device(struct zpci_dev *zdev)
zpci_update_fh(zdev, fh);
return rc;
}
EXPORT_SYMBOL_GPL(zpci_enable_device);
int zpci_disable_device(struct zpci_dev *zdev)
{
@ -723,6 +737,7 @@ int zpci_disable_device(struct zpci_dev *zdev)
}
return rc;
}
EXPORT_SYMBOL_GPL(zpci_disable_device);
/**
* zpci_hot_reset_device - perform a reset of the given zPCI function
@ -816,6 +831,7 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state)
kref_init(&zdev->kref);
mutex_init(&zdev->lock);
mutex_init(&zdev->kzdev_lock);
rc = zpci_init_iommu(zdev);
if (rc)

7
arch/s390/pci/pci_clp.c
View File

@ -106,6 +106,8 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
zdev->max_msi = response->noi;
zdev->fmb_update = response->mui;
zdev->version = response->version;
zdev->maxstbl = response->maxstbl;
zdev->dtsm = response->dtsm;
switch (response->version) {
case 1:
@ -229,12 +231,16 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 comma
{
struct clp_req_rsp_set_pci *rrb;
int rc, retries = 100;
u32 gisa = 0;
*fh = 0;
rrb = clp_alloc_block(GFP_KERNEL);
if (!rrb)
return -ENOMEM;
if (command != CLP_SET_DISABLE_PCI_FN)
gisa = zdev->gisa;
do {
memset(rrb, 0, sizeof(*rrb));
rrb->request.hdr.len = sizeof(rrb->request);
@ -243,6 +249,7 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u32 *fh, u8 nr_dma_as, u8 comma
rrb->request.fh = zdev->fh;
rrb->request.oc = command;
rrb->request.ndas = nr_dma_as;
rrb->request.gisa = gisa;
rc = clp_req(rrb, CLP_LPS_PCI);
if (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY) {

4
arch/s390/pci/pci_insn.c
View File

@ -92,6 +92,7 @@ u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status)
return cc;
}
EXPORT_SYMBOL_GPL(zpci_mod_fc);
/* Refresh PCI Translations */
static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
@ -138,7 +139,7 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
}
/* Set Interruption Controls */
int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
int zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
{
if (!test_facility(72))
return -EIO;
@ -149,6 +150,7 @@ int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
return 0;
}
EXPORT_SYMBOL_GPL(zpci_set_irq_ctrl);
/* PCI Load */
static inline int ____pcilg(u64 *data, u64 req, u64 offset, u8 *status)

48
arch/s390/pci/pci_irq.c
View File

@ -11,16 +11,10 @@
#include <asm/isc.h>
#include <asm/airq.h>
#include <asm/tpi.h>
static enum {FLOATING, DIRECTED} irq_delivery;
#define SIC_IRQ_MODE_ALL 0
#define SIC_IRQ_MODE_SINGLE 1
#define SIC_IRQ_MODE_DIRECT 4
#define SIC_IRQ_MODE_D_ALL 16
#define SIC_IRQ_MODE_D_SINGLE 17
#define SIC_IRQ_MODE_SET_CPU 18
/*
* summary bit vector
* FLOATING - summary bit per function
@ -49,6 +43,7 @@ static int zpci_set_airq(struct zpci_dev *zdev)
fib.fmt0.aibvo = 0; /* each zdev has its own interrupt vector */
fib.fmt0.aisb = virt_to_phys(zpci_sbv->vector) + (zdev->aisb / 64) * 8;
fib.fmt0.aisbo = zdev->aisb & 63;
fib.gd = zdev->gisa;
return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
}
@ -60,6 +55,8 @@ static int zpci_clear_airq(struct zpci_dev *zdev)
struct zpci_fib fib = {0};
u8 cc, status;
fib.gd = zdev->gisa;
cc = zpci_mod_fc(req, &fib, &status);
if (cc == 3 || (cc == 1 && status == 24))
/* Function already gone or IRQs already deregistered. */
@ -78,6 +75,7 @@ static int zpci_set_directed_irq(struct zpci_dev *zdev)
fib.fmt = 1;
fib.fmt1.noi = zdev->msi_nr_irqs;
fib.fmt1.dibvo = zdev->msi_first_bit;
fib.gd = zdev->gisa;
return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
}
@ -90,6 +88,7 @@ static int zpci_clear_directed_irq(struct zpci_dev *zdev)
u8 cc, status;
fib.fmt = 1;
fib.gd = zdev->gisa;
cc = zpci_mod_fc(req, &fib, &status);
if (cc == 3 || (cc == 1 && status == 24))
/* Function already gone or IRQs already deregistered. */
@ -153,6 +152,7 @@ static struct irq_chip zpci_irq_chip = {
static void zpci_handle_cpu_local_irq(bool rescan)
{
struct airq_iv *dibv = zpci_ibv[smp_processor_id()];
union zpci_sic_iib iib = {{0}};
unsigned long bit;
int irqs_on = 0;
@ -164,7 +164,7 @@ static void zpci_handle_cpu_local_irq(bool rescan)
/* End of second scan with interrupts on. */
break;
/* First scan complete, reenable interrupts. */
if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC))
if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &iib))
break;
bit = 0;
continue;
@ -192,6 +192,7 @@ static void zpci_handle_remote_irq(void *data)
static void zpci_handle_fallback_irq(void)
{
struct cpu_irq_data *cpu_data;
union zpci_sic_iib iib = {{0}};
unsigned long cpu;
int irqs_on = 0;
@ -202,7 +203,7 @@ static void zpci_handle_fallback_irq(void)
/* End of second scan with interrupts on. */
break;
/* First scan complete, reenable interrupts. */
if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib))
break;
cpu = 0;
continue;
@ -216,8 +217,11 @@ static void zpci_handle_fallback_irq(void)
}
}
static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating)
static void zpci_directed_irq_handler(struct airq_struct *airq,
struct tpi_info *tpi_info)
{
bool floating = !tpi_info->directed_irq;
if (floating) {
inc_irq_stat(IRQIO_PCF);
zpci_handle_fallback_irq();
@ -227,8 +231,10 @@ static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating)
}
}
static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating)
static void zpci_floating_irq_handler(struct airq_struct *airq,
struct tpi_info *tpi_info)
{
union zpci_sic_iib iib = {{0}};
unsigned long si, ai;
struct airq_iv *aibv;
int irqs_on = 0;
@ -242,7 +248,7 @@ static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating)
/* End of second scan with interrupts on. */
break;
/* First scan complete, reenable interrupts. */
if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib))
break;
si = 0;
continue;
@ -291,7 +297,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
zdev->aisb = bit;
/* Create adapter interrupt vector */
zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL);
if (!zdev->aibv)
return -ENOMEM;
@ -402,11 +408,12 @@ static struct airq_struct zpci_airq = {
static void __init cpu_enable_directed_irq(void *unused)
{
union zpci_sic_iib iib = {{0}};
union zpci_sic_iib ziib = {{0}};
iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector;
__zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC);
zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib);
}
static int __init zpci_directed_irq_init(void)
@ -414,14 +421,14 @@ static int __init zpci_directed_irq_init(void)
union zpci_sic_iib iib = {{0}};
unsigned int cpu;
zpci_sbv = airq_iv_create(num_possible_cpus(), 0);
zpci_sbv = airq_iv_create(num_possible_cpus(), 0, NULL);
if (!zpci_sbv)
return -ENOMEM;
iib.diib.isc = PCI_ISC;
iib.diib.nr_cpus = num_possible_cpus();
iib.diib.disb_addr = virt_to_phys(zpci_sbv->vector);
__zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib);
zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib);
zpci_ibv = kcalloc(num_possible_cpus(), sizeof(*zpci_ibv),
GFP_KERNEL);
@ -436,7 +443,7 @@ static int __init zpci_directed_irq_init(void)
zpci_ibv[cpu] = airq_iv_create(cache_line_size() * BITS_PER_BYTE,
AIRQ_IV_DATA |
AIRQ_IV_CACHELINE |
(!cpu ? AIRQ_IV_ALLOC : 0));
(!cpu ? AIRQ_IV_ALLOC : 0), NULL);
if (!zpci_ibv[cpu])
return -ENOMEM;
}
@ -453,7 +460,7 @@ static int __init zpci_floating_irq_init(void)
if (!zpci_ibv)
return -ENOMEM;
zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, NULL);
if (!zpci_sbv)
goto out_free;
@ -466,6 +473,7 @@ out_free:
int __init zpci_irq_init(void)
{
union zpci_sic_iib iib = {{0}};
int rc;
irq_delivery = sclp.has_dirq ? DIRECTED : FLOATING;
@ -497,7 +505,7 @@ int __init zpci_irq_init(void)
* Enable floating IRQs (with suppression after one IRQ). When using
* directed IRQs this enables the fallback path.
*/
zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC);
zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC, &iib);
return 0;
out_airq:

4
drivers/s390/char/sclp_early.c
View File

@ -45,6 +45,10 @@ static void __init sclp_early_facilities_detect(void)
sclp.has_gisaf = !!(sccb->fac118 & 0x08);
sclp.has_hvs = !!(sccb->fac119 & 0x80);
sclp.has_kss = !!(sccb->fac98 & 0x01);
sclp.has_aisii = !!(sccb->fac118 & 0x40);
sclp.has_aeni = !!(sccb->fac118 & 0x20);
sclp.has_aisi = !!(sccb->fac118 & 0x10);
sclp.has_zpci_lsi = !!(sccb->fac118 & 0x01);
if (sccb->fac85 & 0x02)
S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP;
if (sccb->fac91 & 0x40)

12
drivers/s390/cio/airq.c
View File

@ -99,7 +99,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy)
rcu_read_lock();
hlist_for_each_entry_rcu(airq, head, list)
if ((*airq->lsi_ptr & airq->lsi_mask) != 0)
airq->handler(airq, !tpi_info->directed_irq);
airq->handler(airq, tpi_info);
rcu_read_unlock();
return IRQ_HANDLED;
@ -122,10 +122,12 @@ static inline unsigned long iv_size(unsigned long bits)
* airq_iv_create - create an interrupt vector
* @bits: number of bits in the interrupt vector
* @flags: allocation flags
* @vec: pointer to pinned guest memory if AIRQ_IV_GUESTVEC
*
* Returns a pointer to an interrupt vector structure
*/
struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags)
struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags,
unsigned long *vec)
{
struct airq_iv *iv;
unsigned long size;
@ -146,6 +148,8 @@ struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags)
&iv->vector_dma);
if (!iv->vector)
goto out_free;
} else if (flags & AIRQ_IV_GUESTVEC) {
iv->vector = vec;
} else {
iv->vector = cio_dma_zalloc(size);
if (!iv->vector)
@ -185,7 +189,7 @@ out_free:
kfree(iv->avail);
if (iv->flags & AIRQ_IV_CACHELINE && iv->vector)
dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma);
else
else if (!(iv->flags & AIRQ_IV_GUESTVEC))
cio_dma_free(iv->vector, size);
kfree(iv);
out:
@ -204,7 +208,7 @@ void airq_iv_release(struct airq_iv *iv)
kfree(iv->bitlock);
if (iv->flags & AIRQ_IV_CACHELINE)
dma_pool_free(airq_iv_cache, iv->vector, iv->vector_dma);
else
else if (!(iv->flags & AIRQ_IV_GUESTVEC))
cio_dma_free(iv->vector, iv_size(iv->bits));
kfree(iv->avail);
kfree(iv);

6
drivers/s390/cio/qdio_thinint.c
View File

@ -15,6 +15,7 @@
#include <asm/qdio.h>
#include <asm/airq.h>
#include <asm/isc.h>
#include <asm/tpi.h>
#include "cio.h"
#include "ioasm.h"
@ -93,9 +94,10 @@ static inline u32 clear_shared_ind(void)
/**
* tiqdio_thinint_handler - thin interrupt handler for qdio
* @airq: pointer to adapter interrupt descriptor
* @floating: flag to recognize floating vs. directed interrupts (unused)
* @tpi_info: interrupt information (e.g. floating vs directed -- unused)
*/
static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
static void tiqdio_thinint_handler(struct airq_struct *airq,
struct tpi_info *tpi_info)
{
u64 irq_time = S390_lowcore.int_clock;
u32 si_used = clear_shared_ind();

9
drivers/s390/crypto/ap_bus.c
View File

@ -27,6 +27,7 @@
#include <linux/kthread.h>
#include <linux/mutex.h>
#include <asm/airq.h>
#include <asm/tpi.h>
#include <linux/atomic.h>
#include <asm/isc.h>
#include <linux/hrtimer.h>
@ -131,7 +132,8 @@ static int ap_max_adapter_id = 63;
static struct bus_type ap_bus_type;
/* Adapter interrupt definitions */
static void ap_interrupt_handler(struct airq_struct *airq, bool floating);
static void ap_interrupt_handler(struct airq_struct *airq,
struct tpi_info *tpi_info);
static bool ap_irq_flag;
@ -452,9 +454,10 @@ static enum hrtimer_restart ap_poll_timeout(struct hrtimer *unused)
/**
* ap_interrupt_handler() - Schedule ap_tasklet on interrupt
* @airq: pointer to adapter interrupt descriptor
* @floating: ignored
* @tpi_info: ignored
*/
static void ap_interrupt_handler(struct airq_struct *airq, bool floating)
static void ap_interrupt_handler(struct airq_struct *airq,
struct tpi_info *tpi_info)
{
inc_irq_stat(IRQIO_APB);
tasklet_schedule(&ap_tasklet);

6
drivers/s390/virtio/virtio_ccw.c
View File

@ -33,6 +33,7 @@
#include <asm/virtio-ccw.h>
#include <asm/isc.h>
#include <asm/airq.h>
#include <asm/tpi.h>
/*
* virtio related functions
@ -204,7 +205,8 @@ static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info)
write_unlock_irqrestore(&info->lock, flags);
}
static void virtio_airq_handler(struct airq_struct *airq, bool floating)
static void virtio_airq_handler(struct airq_struct *airq,
struct tpi_info *tpi_info)
{
struct airq_info *info = container_of(airq, struct airq_info, airq);
unsigned long ai;
@ -240,7 +242,7 @@ static struct airq_info *new_airq_info(int index)
return NULL;
rwlock_init(&info->lock);
info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR
| AIRQ_IV_CACHELINE);
| AIRQ_IV_CACHELINE, NULL);
if (!info->aiv) {
kfree(info);
return NULL;

11
drivers/vfio/pci/Kconfig
View File

@ -44,6 +44,17 @@ config VFIO_PCI_IGD
To enable Intel IGD assignment through vfio-pci, say Y.
endif
config VFIO_PCI_ZDEV_KVM
bool "VFIO PCI extensions for s390x KVM passthrough"
depends on S390 && KVM
default y
help
Support s390x-specific extensions to enable support for enhancements
to KVM passthrough capabilities, such as interpretive execution of
zPCI instructions.
To enable s390x KVM vfio-pci extensions, say Y.
source "drivers/vfio/pci/mlx5/Kconfig"
source "drivers/vfio/pci/hisilicon/Kconfig"

2
drivers/vfio/pci/Makefile
View File

@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
vfio-pci-core-$(CONFIG_S390) += vfio_pci_zdev.o
vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o
obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
vfio-pci-y := vfio_pci.o

10
drivers/vfio/pci/vfio_pci_core.c
View File

@ -316,10 +316,14 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
pci_write_config_word(pdev, PCI_COMMAND, cmd);
}
ret = vfio_config_init(vdev);
ret = vfio_pci_zdev_open_device(vdev);
if (ret)
goto out_free_state;
ret = vfio_config_init(vdev);
if (ret)
goto out_free_zdev;
msix_pos = pdev->msix_cap;
if (msix_pos) {
u16 flags;
@ -340,6 +344,8 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
return 0;
out_free_zdev:
vfio_pci_zdev_close_device(vdev);
out_free_state:
kfree(vdev->pci_saved_state);
vdev->pci_saved_state = NULL;
@ -418,6 +424,8 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
vdev->needs_reset = true;
vfio_pci_zdev_close_device(vdev);
/*
* If we have saved state, restore it. If we can reset the device,
* even better. Resetting with current state seems better than

35
drivers/vfio/pci/vfio_pci_zdev.c
View File

@ -11,6 +11,7 @@
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/vfio_zdev.h>
#include <linux/kvm_host.h>
#include <asm/pci_clp.h>
#include <asm/pci_io.h>
@ -23,14 +24,15 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
{
struct vfio_device_info_cap_zpci_base cap = {
.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE,
.header.version = 1,
.header.version = 2,
.start_dma = zdev->start_dma,
.end_dma = zdev->end_dma,
.pchid = zdev->pchid,
.vfn = zdev->vfn,
.fmb_length = zdev->fmb_length,
.pft = zdev->pft,
.gid = zdev->pfgid
.gid = zdev->pfgid,
.fh = zdev->fh
};
return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
@ -43,14 +45,16 @@ static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
{
struct vfio_device_info_cap_zpci_group cap = {
.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_GROUP,
.header.version = 1,
.header.version = 2,
.dasm = zdev->dma_mask,
.msi_addr = zdev->msi_addr,
.flags = VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH,
.mui = zdev->fmb_update,
.noi = zdev->max_msi,
.maxstbl = ZPCI_MAX_WRITE_SIZE,
.version = zdev->version
.version = zdev->version,
.reserved = 0,
.imaxstbl = zdev->maxstbl
};
return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
@ -136,3 +140,26 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
return ret;
}
int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
{
struct zpci_dev *zdev = to_zpci(vdev->pdev);
if (!zdev)
return -ENODEV;
if (!vdev->vdev.kvm)
return 0;
return kvm_s390_pci_register_kvm(zdev, vdev->vdev.kvm);
}
void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
{
struct zpci_dev *zdev = to_zpci(vdev->pdev);
if (!zdev || !vdev->vdev.kvm)
return;
kvm_s390_pci_unregister_kvm(zdev);
}

3
include/linux/sched/user.h
View File

@ -24,7 +24,8 @@ struct user_struct {
kuid_t uid;
#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
defined(CONFIG_NET) || defined(CONFIG_IO_URING)
defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
defined(CONFIG_VFIO_PCI_ZDEV_KVM)
atomic_long_t locked_vm;
#endif
#ifdef CONFIG_WATCH_QUEUE

12
include/linux/vfio_pci_core.h
View File

@ -206,15 +206,25 @@ static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev)
}
#endif
#ifdef CONFIG_S390
#ifdef CONFIG_VFIO_PCI_ZDEV_KVM
extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
struct vfio_info_cap *caps);
int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev);
void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev);
#else
static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
struct vfio_info_cap *caps)
{
return -ENODEV;
}
static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
{
return 0;
}
static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
{}
#endif
/* Will be exported for vfio pci drivers usage */

31
include/uapi/linux/kvm.h
View File

@ -1167,6 +1167,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
#define KVM_CAP_X86_NOTIFY_VMEXIT 219
#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
#define KVM_CAP_S390_ZPCI_OP 221
#ifdef KVM_CAP_IRQ_ROUTING
@ -2186,4 +2187,34 @@ struct kvm_stats_desc {
#define KVM_X86_NOTIFY_VMEXIT_ENABLED (1ULL << 0)
#define KVM_X86_NOTIFY_VMEXIT_USER (1ULL << 1)
/* Available with KVM_CAP_S390_ZPCI_OP */
#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op)
struct kvm_s390_zpci_op {
/* in */
__u32 fh; /* target device */
__u8 op; /* operation to perform */
__u8 pad[3];
union {
/* for KVM_S390_ZPCIOP_REG_AEN */
struct {
__u64 ibv; /* Guest addr of interrupt bit vector */
__u64 sb; /* Guest addr of summary bit */
__u32 flags;
__u32 noi; /* Number of interrupts */
__u8 isc; /* Guest interrupt subclass */
__u8 sbo; /* Offset of guest summary bit vector */
__u16 pad;
} reg_aen;
__u64 reserved[8];
} u;
};
/* types for kvm_s390_zpci_op->op */
#define KVM_S390_ZPCIOP_REG_AEN 0
#define KVM_S390_ZPCIOP_DEREG_AEN 1
/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
#endif /* __LINUX_KVM_H */

7
include/uapi/linux/vfio_zdev.h
View File

@ -29,6 +29,9 @@ struct vfio_device_info_cap_zpci_base {
__u16 fmb_length; /* Measurement Block Length (in bytes) */
__u8 pft; /* PCI Function Type */
__u8 gid; /* PCI function group ID */
/* End of version 1 */
__u32 fh; /* PCI function handle */
/* End of version 2 */
};
/**
@ -47,6 +50,10 @@ struct vfio_device_info_cap_zpci_group {
__u16 noi; /* Maximum number of MSIs */
__u16 maxstbl; /* Maximum Store Block Length */
__u8 version; /* Supported PCI Version */
/* End of version 1 */
__u8 reserved;
__u16 imaxstbl; /* Maximum Interpreted Store Block Length */
/* End of version 2 */
};
/**