Note: this version of the series is built on top of vfio -next:
https://github.com/awilliam/linux-vfio/tree/next
As it now depends on 'vfio: remove VFIO_GROUP_NOTIFY_SET_KVM' and its
prereqs.
Additionally, if you care to try testing this series on top of vfio -next
you'll also want to pick up this fix:
https://lore.kernel.org/kvm/[email protected]/
---
Enable interpretive execution of zPCI instructions + adapter interruption
forwarding for s390x KVM vfio-pci. This is done by triggering a routine
when the VFIO group is associated with the KVM guest, transmitting to
firmware a special token (GISA designation) to enable that specific guest
for interpretive execution on that zPCI device. Load/store interpreation
enablement is then controlled by userspace (based upon whether or not a
SHM bit is placed in the virtual function handle). Adapter Event
Notification interpretation is controlled from userspace via a new KVM
ioctl.
By allowing intepretation of zPCI instructions and firmware delivery of
interrupts to guests, we can reduce the frequency of guest SIE exits for
zPCI.
From the perspective of guest configuration, you passthrough zPCI devices
in the same manner as before, with intepretation support being used by
default if available in kernel+qemu.
Will follow up with a link an updated QEMU series.
Changelog v7->v8:
- Fix ioctl documentation (Thomas)
- remove copy_to_user from ioctl, was from old version (Thomas)
- KVM_S390_ZPCIOP_REG_AEN: fail on undefined flags (Thomas)
- kvm_s390_pci_zpci_reg_aen: cleanup hostflag setting (Thomas) and
also fix an accidental bit inversion while at it
- CONFIG_VFIO_PCI_ZDEV_KVM: add the 'say Y' that was accidentally left
out of the help text (Jason)
- Restructure the vfio-pci-zdev pieces on top of 'vfio: remove
VFIO_GROUP_NOTIFY_SET_KVM' (Jason) - open_device/close_device will now
call the kvm registration routines directly. Move the open_device call
to vfio_pci_core_enable so that errors can be propogated. For parity,
move the close_device call to vfio_pci_core_disable.
Matthew Rosato (22):
s390/sclp: detect the zPCI load/store interpretation facility
s390/sclp: detect the AISII facility
s390/sclp: detect the AENI facility
s390/sclp: detect the AISI facility
s390/airq: pass more TPI info to airq handlers
s390/airq: allow for airq structure that uses an input vector
s390/pci: externalize the SIC operation controls and routine
s390/pci: stash associated GISA designation
s390/pci: stash dtsm and maxstbl
vfio/pci: introduce CONFIG_VFIO_PCI_ZDEV_KVM
KVM: s390: pci: add basic kvm_zdev structure
KVM: s390: pci: do initial setup for AEN interpretation
KVM: s390: pci: enable host forwarding of Adapter Event Notifications
KVM: s390: mechanism to enable guest zPCI Interpretation
KVM: s390: pci: provide routines for enabling/disabling interrupt
forwarding
KVM: s390: pci: add routines to start/stop interpretive execution
vfio-pci/zdev: add open/close device hooks
vfio-pci/zdev: add function handle to clp base capability
vfio-pci/zdev: different maxstbl for interpreted devices
KVM: s390: add KVM_S390_ZPCI_OP to manage guest zPCI devices
KVM: s390: introduce CPU feature for zPCI Interpretation
MAINTAINERS: additional files related kvm s390 pci passthrough
Documentation/virt/kvm/api.rst | 46 ++
MAINTAINERS | 1 +
arch/s390/include/asm/airq.h | 7 +-
arch/s390/include/asm/kvm_host.h | 26 ++
arch/s390/include/asm/pci.h | 13 +
arch/s390/include/asm/pci_clp.h | 9 +-
arch/s390/include/asm/pci_insn.h | 29 +-
arch/s390/include/asm/sclp.h | 4 +
arch/s390/include/asm/tpi.h | 13 +
arch/s390/include/uapi/asm/kvm.h | 1 +
arch/s390/kvm/Makefile | 1 +
arch/s390/kvm/interrupt.c | 96 ++++-
arch/s390/kvm/kvm-s390.c | 87 +++-
arch/s390/kvm/kvm-s390.h | 10 +
arch/s390/kvm/pci.c | 695 +++++++++++++++++++++++++++++++
arch/s390/kvm/pci.h | 88 ++++
arch/s390/pci/pci.c | 16 +
arch/s390/pci/pci_clp.c | 7 +
arch/s390/pci/pci_insn.c | 4 +-
arch/s390/pci/pci_irq.c | 48 ++-
drivers/s390/char/sclp_early.c | 4 +
drivers/s390/cio/airq.c | 12 +-
drivers/s390/cio/qdio_thinint.c | 6 +-
drivers/s390/crypto/ap_bus.c | 9 +-
drivers/s390/virtio/virtio_ccw.c | 6 +-
drivers/vfio/pci/Kconfig | 11 +
drivers/vfio/pci/Makefile | 2 +-
drivers/vfio/pci/vfio_pci_core.c | 11 +-
drivers/vfio/pci/vfio_pci_zdev.c | 38 +-
include/linux/sched/user.h | 3 +-
include/linux/vfio_pci_core.h | 14 +-
include/uapi/linux/kvm.h | 32 ++
include/uapi/linux/vfio_zdev.h | 7 +
33 files changed, 1300 insertions(+), 56 deletions(-)
create mode 100644 arch/s390/kvm/pci.c
create mode 100644 arch/s390/kvm/pci.h
--
2.27.0
Initial setup for Adapter Event Notification Interpretation for zPCI
passthrough devices. Specifically, allocate a structure for forwarding of
adapter events and pass the address of this structure to firmware.
Reviewed-by: Christian Borntraeger <[email protected]>
Signed-off-by: Matthew Rosato <[email protected]>
---
arch/s390/include/asm/pci.h | 4 +
arch/s390/include/asm/pci_insn.h | 12 +++
arch/s390/kvm/interrupt.c | 14 +++
arch/s390/kvm/kvm-s390.c | 11 +++
arch/s390/kvm/pci.c | 160 +++++++++++++++++++++++++++++++
arch/s390/kvm/pci.h | 49 ++++++++++
arch/s390/pci/pci.c | 6 ++
7 files changed, 256 insertions(+)
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 50f1851edfbe..322060a75d9f 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -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
@@ -204,6 +205,9 @@ 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
----------------------------------------------------------------------------- */
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index 5331082fa516..e5f57cfe1d45 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -101,6 +101,7 @@ struct zpci_fib {
/* 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
@@ -127,9 +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);
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 17ff475157d8..37ff4358121a 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -32,6 +32,7 @@
#include "kvm-s390.h"
#include "gaccess.h"
#include "trace-s390.h"
+#include "pci.h"
#define PFAULT_INIT 0x0600
#define PFAULT_DONE 0x0680
@@ -3328,6 +3329,11 @@ 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);
@@ -3365,6 +3371,14 @@ 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;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 76ad6408cb2c..efc0d8e22308 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -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"
@@ -502,6 +503,14 @@ 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 +525,8 @@ int kvm_arch_init(void *opaque)
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);
}
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 21c2be5c2713..268cbe99fbac 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -9,8 +9,149 @@
#include <linux/kvm_host.h>
#include <linux/pci.h>
+#include <asm/pci.h>
+#include <asm/pci_insn.h>
#include "pci.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 = 0;
+ aift->sbv = 0;
+ aift->kzdev = 0;
+ 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 = 0;
+free_aipb:
+ kfree(zpci_aipb);
+ zpci_aipb = 0;
+
+ 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;
+}
+
static int kvm_s390_pci_dev_open(struct zpci_dev *zdev)
{
struct kvm_zdev *kzdev;
@@ -34,3 +175,22 @@ static void kvm_s390_pci_dev_release(struct zpci_dev *zdev)
zdev->kzdev = 0;
kfree(kzdev);
}
+
+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);
+}
diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h
index ce93978e8913..c357d900f8b0 100644
--- a/arch/s390/kvm/pci.h
+++ b/arch/s390/kvm/pci.h
@@ -12,10 +12,59 @@
#include <linux/kvm_host.h>
#include <linux/pci.h>
+#include <linux/mutex.h>
+#include <asm/airq.h>
+#include <asm/cpu.h>
struct kvm_zdev {
struct zpci_dev *zdev;
struct kvm *kvm;
};
+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;
+
+int kvm_s390_pci_aen_init(u8 nisc);
+void kvm_s390_pci_aen_exit(void);
+
+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 */
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index a86cd1cbb80e..f0a439c43395 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -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;
--
2.27.0