* [PATCH v3 12/37] KVM: s390/mm: Make pages accessible before destroying the guest
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
Before we destroy the secure configuration, we better make all
pages accessible again. This also happens during reboot, where we reboot
into a non-secure guest that then can go again into secure mode. As
this "new" secure guest will have a new ID we cannot reuse the old page
state.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
arch/s390/include/asm/gmap.h | 1 +
arch/s390/kvm/pv.c | 2 ++
arch/s390/mm/gmap.c | 35 +++++++++++++++++++++++++++++++++++
3 files changed, 38 insertions(+)
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 6f9ff7a69fa2..a816fb4734b8 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -149,4 +149,5 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start,
void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
unsigned long gaddr, unsigned long vmaddr);
int gmap_mark_unmergeable(void);
+void s390_reset_acc(struct mm_struct *mm);
#endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 67ea9a18ed8f..7d95d7437140 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -66,6 +66,8 @@ int kvm_s390_pv_destroy_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
{
int cc;
+ /* make all pages accessible before destroying the guest */
+ s390_reset_acc(kvm->mm);
cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 7291452fe5f0..27926a06df32 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2650,3 +2650,38 @@ void s390_reset_cmma(struct mm_struct *mm)
up_write(&mm->mmap_sem);
}
EXPORT_SYMBOL_GPL(s390_reset_cmma);
+
+/*
+ * make inaccessible pages accessible again
+ */
+static int __s390_reset_acc(pte_t *ptep, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ pte_t pte = READ_ONCE(*ptep);
+
+ if (pte_present(pte))
+ WARN_ON_ONCE(uv_convert_from_secure(pte_val(pte) & PAGE_MASK));
+ return 0;
+}
+
+static const struct mm_walk_ops reset_acc_walk_ops = {
+ .pte_entry = __s390_reset_acc,
+};
+
+#include <linux/sched/mm.h>
+void s390_reset_acc(struct mm_struct *mm)
+{
+ /*
+ * we might be called during
+ * reset: we walk the pages and clear
+ * close of all kvm file descriptors: we walk the pages and clear
+ * exit of process on fd closure: vma already gone, do nothing
+ */
+ if (!mmget_not_zero(mm))
+ return;
+ down_read(&mm->mmap_sem);
+ walk_page_range(mm, 0, TASK_SIZE, &reset_acc_walk_ops, NULL);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+}
+EXPORT_SYMBOL_GPL(s390_reset_acc);
--
2.25.0
^ permalink raw reply related
* [PATCH v3 28/37] KVM: s390: protvirt: UV calls in support of diag308 0, 1
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
diag 308 subcode 0 and 1 require several KVM and Ultravisor interactions.
Specific to these "soft" reboots are
* The "unshare all" UVC
* The "prepare for reset" UVC
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/uv.h | 4 ++++
arch/s390/kvm/kvm-s390.c | 22 ++++++++++++++++++++++
include/uapi/linux/kvm.h | 2 ++
3 files changed, 28 insertions(+)
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 09dc6dba94a4..a7595c647759 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -36,6 +36,8 @@
#define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300
#define UVC_CMD_UNPACK_IMG 0x0301
#define UVC_CMD_VERIFY_IMG 0x0302
+#define UVC_CMD_PREPARE_RESET 0x0320
+#define UVC_CMD_SET_UNSHARE_ALL 0x0340
#define UVC_CMD_PIN_PAGE_SHARED 0x0341
#define UVC_CMD_UNPIN_PAGE_SHARED 0x0342
#define UVC_CMD_SET_SHARED_ACCESS 0x1000
@@ -56,6 +58,8 @@ enum uv_cmds_inst {
BIT_UVC_CMD_SET_SEC_PARMS = 11,
BIT_UVC_CMD_UNPACK_IMG = 13,
BIT_UVC_CMD_VERIFY_IMG = 14,
+ BIT_UVC_CMD_PREPARE_RESET = 18,
+ BIT_UVC_CMD_UNSHARE_ALL = 20,
BIT_UVC_CMD_PIN_PAGE_SHARED = 21,
BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22,
};
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 303f994f3d03..9ac73b717e25 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2310,6 +2310,28 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
cmd->rrc);
break;
}
+ case KVM_PV_VM_PREP_RESET: {
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm))
+ break;
+
+ r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+ UVC_CMD_PREPARE_RESET, &cmd->rc, &cmd->rrc);
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT PREP RESET: rc %x rrc %x",
+ cmd->rc, cmd->rrc);
+ break;
+ }
+ case KVM_PV_VM_UNSHARE_ALL: {
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm))
+ break;
+
+ r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+ UVC_CMD_SET_UNSHARE_ALL, &cmd->rc, &cmd->rrc);
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT UNSHARE: rc %x rrc %x",
+ cmd->rc, cmd->rrc);
+ break;
+ }
default:
return -ENOTTY;
}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 69ccbbabfc03..60efbbc86209 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1500,6 +1500,8 @@ enum pv_cmd_id {
KVM_PV_VM_SET_SEC_PARMS,
KVM_PV_VM_UNPACK,
KVM_PV_VM_VERIFY,
+ KVM_PV_VM_PREP_RESET,
+ KVM_PV_VM_UNSHARE_ALL,
};
struct kvm_pv_cmd {
--
2.25.0
^ permalink raw reply related
* [PATCH v3 09/37] KVM: s390: protvirt: Add initial vm and cpu lifecycle handling
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
This contains 3 main changes:
1. changes in SIE control block handling for secure guests
2. helper functions for create/destroy/unpack secure guests
3. KVM_S390_PV_COMMAND ioctl to allow userspace dealing with secure
machines
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/kvm_host.h | 24 ++-
arch/s390/include/asm/uv.h | 69 +++++++++
arch/s390/kvm/Makefile | 2 +-
arch/s390/kvm/kvm-s390.c | 188 ++++++++++++++++++++++-
arch/s390/kvm/kvm-s390.h | 35 +++++
arch/s390/kvm/pv.c | 256 +++++++++++++++++++++++++++++++
include/uapi/linux/kvm.h | 31 ++++
7 files changed, 601 insertions(+), 4 deletions(-)
create mode 100644 arch/s390/kvm/pv.c
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index d058289385a5..1aa2382fe363 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -160,7 +160,13 @@ struct kvm_s390_sie_block {
__u8 reserved08[4]; /* 0x0008 */
#define PROG_IN_SIE (1<<0)
__u32 prog0c; /* 0x000c */
- __u8 reserved10[16]; /* 0x0010 */
+ union {
+ __u8 reserved10[16]; /* 0x0010 */
+ struct {
+ __u64 pv_handle_cpu;
+ __u64 pv_handle_config;
+ };
+ };
#define PROG_BLOCK_SIE (1<<0)
#define PROG_REQUEST (1<<1)
atomic_t prog20; /* 0x0020 */
@@ -233,7 +239,7 @@ struct kvm_s390_sie_block {
#define ECB3_RI 0x01
__u8 ecb3; /* 0x0063 */
__u32 scaol; /* 0x0064 */
- __u8 reserved68; /* 0x0068 */
+ __u8 sdf; /* 0x0068 */
__u8 epdx; /* 0x0069 */
__u8 reserved6a[2]; /* 0x006a */
__u32 todpr; /* 0x006c */
@@ -645,6 +651,11 @@ struct kvm_guestdbg_info_arch {
unsigned long last_bp;
};
+struct kvm_s390_pv_vcpu {
+ u64 handle;
+ unsigned long stor_base;
+};
+
struct kvm_vcpu_arch {
struct kvm_s390_sie_block *sie_block;
/* if vsie is active, currently executed shadow sie control block */
@@ -673,6 +684,7 @@ struct kvm_vcpu_arch {
__u64 cputm_start;
bool gs_enabled;
bool skey_enabled;
+ struct kvm_s390_pv_vcpu pv;
};
struct kvm_vm_stat {
@@ -843,6 +855,13 @@ struct kvm_s390_gisa_interrupt {
DECLARE_BITMAP(kicked_mask, KVM_MAX_VCPUS);
};
+struct kvm_s390_pv {
+ u64 handle;
+ u64 guest_len;
+ unsigned long stor_base;
+ void *stor_var;
+};
+
struct kvm_arch{
void *sca;
int use_esca;
@@ -878,6 +897,7 @@ struct kvm_arch{
DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS);
struct kvm_s390_gisa_interrupt gisa_int;
+ struct kvm_s390_pv pv;
};
#define KVM_HVA_ERR_BAD (-1UL)
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index a81af06507a9..09dc6dba94a4 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -23,11 +23,19 @@
#define UVC_RC_INV_STATE 0x0003
#define UVC_RC_INV_LEN 0x0005
#define UVC_RC_NO_RESUME 0x0007
+#define UVC_RC_NEED_DESTROY 0x8000
#define UVC_CMD_QUI 0x0001
#define UVC_CMD_INIT_UV 0x000f
+#define UVC_CMD_CREATE_SEC_CONF 0x0100
+#define UVC_CMD_DESTROY_SEC_CONF 0x0101
+#define UVC_CMD_CREATE_SEC_CPU 0x0120
+#define UVC_CMD_DESTROY_SEC_CPU 0x0121
#define UVC_CMD_CONV_TO_SEC_STOR 0x0200
#define UVC_CMD_CONV_FROM_SEC_STOR 0x0201
+#define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300
+#define UVC_CMD_UNPACK_IMG 0x0301
+#define UVC_CMD_VERIFY_IMG 0x0302
#define UVC_CMD_PIN_PAGE_SHARED 0x0341
#define UVC_CMD_UNPIN_PAGE_SHARED 0x0342
#define UVC_CMD_SET_SHARED_ACCESS 0x1000
@@ -37,10 +45,17 @@
enum uv_cmds_inst {
BIT_UVC_CMD_QUI = 0,
BIT_UVC_CMD_INIT_UV = 1,
+ BIT_UVC_CMD_CREATE_SEC_CONF = 2,
+ BIT_UVC_CMD_DESTROY_SEC_CONF = 3,
+ BIT_UVC_CMD_CREATE_SEC_CPU = 4,
+ BIT_UVC_CMD_DESTROY_SEC_CPU = 5,
BIT_UVC_CMD_CONV_TO_SEC_STOR = 6,
BIT_UVC_CMD_CONV_FROM_SEC_STOR = 7,
BIT_UVC_CMD_SET_SHARED_ACCESS = 8,
BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9,
+ BIT_UVC_CMD_SET_SEC_PARMS = 11,
+ BIT_UVC_CMD_UNPACK_IMG = 13,
+ BIT_UVC_CMD_VERIFY_IMG = 14,
BIT_UVC_CMD_PIN_PAGE_SHARED = 21,
BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22,
};
@@ -52,6 +67,7 @@ struct uv_cb_header {
u16 rrc; /* Return Reason Code */
} __packed __aligned(8);
+/* Query Ultravisor Information */
struct uv_cb_qui {
struct uv_cb_header header;
u64 reserved08;
@@ -71,6 +87,7 @@ struct uv_cb_qui {
u8 reserveda0[200 - 160];
} __packed __aligned(8);
+/* Initialize Ultravisor */
struct uv_cb_init {
struct uv_cb_header header;
u64 reserved08[2];
@@ -79,6 +96,35 @@ struct uv_cb_init {
u64 reserved28[4];
} __packed __aligned(8);
+/* Create Guest Configuration */
+struct uv_cb_cgc {
+ struct uv_cb_header header;
+ u64 reserved08[2];
+ u64 guest_handle;
+ u64 conf_base_stor_origin;
+ u64 conf_virt_stor_origin;
+ u64 reserved30;
+ u64 guest_stor_origin;
+ u64 guest_stor_len;
+ u64 guest_sca;
+ u64 guest_asce;
+ u64 reserved58[5];
+} __packed __aligned(8);
+
+/* Create Secure CPU */
+struct uv_cb_csc {
+ struct uv_cb_header header;
+ u64 reserved08[2];
+ u64 cpu_handle;
+ u64 guest_handle;
+ u64 stor_origin;
+ u8 reserved30[6];
+ u16 num;
+ u64 state_origin;
+ u64 reserved40[4];
+} __packed __aligned(8);
+
+/* Convert to Secure */
struct uv_cb_cts {
struct uv_cb_header header;
u64 reserved08[2];
@@ -86,12 +132,34 @@ struct uv_cb_cts {
u64 gaddr;
} __packed __aligned(8);
+/* Convert from Secure / Pin Page Shared */
struct uv_cb_cfs {
struct uv_cb_header header;
u64 reserved08[2];
u64 paddr;
} __packed __aligned(8);
+/* Set Secure Config Parameter */
+struct uv_cb_ssc {
+ struct uv_cb_header header;
+ u64 reserved08[2];
+ u64 guest_handle;
+ u64 sec_header_origin;
+ u32 sec_header_len;
+ u32 reserved2c;
+ u64 reserved30[4];
+} __packed __aligned(8);
+
+/* Unpack */
+struct uv_cb_unp {
+ struct uv_cb_header header;
+ u64 reserved08[2];
+ u64 guest_handle;
+ u64 gaddr;
+ u64 tweak[2];
+ u64 reserved38[3];
+} __packed __aligned(8);
+
/*
* A common UV call struct for calls that take no payload
* Examples:
@@ -105,6 +173,7 @@ struct uv_cb_nodata {
u64 reserved20[4];
} __packed __aligned(8);
+/* Set Shared Access */
struct uv_cb_share {
struct uv_cb_header header;
u64 reserved08[3];
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 05ee90a5ea08..12decca22e7c 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -9,6 +9,6 @@ common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqch
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o
-kvm-objs += diag.o gaccess.o guestdbg.o vsie.o
+kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o
obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index cc7793525a69..8272a821a621 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -44,6 +44,7 @@
#include <asm/cpacf.h>
#include <asm/timex.h>
#include <asm/ap.h>
+#include <asm/uv.h>
#include "kvm-s390.h"
#include "gaccess.h"
@@ -234,8 +235,10 @@ int kvm_arch_check_processor_compat(void)
return 0;
}
+/* forward declarations */
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long end);
+static int sca_switch_to_extended(struct kvm *kvm);
static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta)
{
@@ -2165,6 +2168,143 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm,
return r;
}
+static void kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ mutex_lock(&vcpu->mutex);
+ kvm_s390_pv_destroy_cpu(vcpu, rc, rrc);
+ mutex_unlock(&vcpu->mutex);
+ }
+}
+
+static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+ int i, r = 0;
+ u16 dummy;
+
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ mutex_lock(&vcpu->mutex);
+ r = kvm_s390_pv_create_cpu(vcpu, rc, rrc);
+ mutex_unlock(&vcpu->mutex);
+ if (r)
+ break;
+ }
+ if (r)
+ kvm_s390_cpus_from_pv(kvm, &dummy, &dummy);
+ return r;
+}
+
+static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
+{
+ int r = 0;
+ u16 dummy;
+ void __user *argp = (void __user *)cmd->data;
+
+ switch (cmd->cmd) {
+ case KVM_PV_ENABLE: {
+ r = -EINVAL;
+ if (kvm_s390_pv_is_protected(kvm))
+ break;
+
+ r = kvm_s390_pv_alloc_vm(kvm);
+ if (r)
+ break;
+
+ /* FMT 4 SIE needs esca */
+ r = sca_switch_to_extended(kvm);
+ if (r) {
+ kvm_s390_pv_dealloc_vm(kvm);
+ kvm_s390_vcpu_unblock_all(kvm);
+ mutex_unlock(&kvm->lock);
+ break;
+ }
+ r = kvm_s390_pv_create_vm(kvm, &cmd->rc, &cmd->rrc);
+ if (!r)
+ r = kvm_s390_cpus_to_pv(kvm, &cmd->rc, &cmd->rrc);
+ if (r)
+ kvm_s390_pv_destroy_vm(kvm, &dummy, &dummy);
+
+ break;
+ }
+ case KVM_PV_DISABLE: {
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm))
+ break;
+
+ kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc);
+ r = kvm_s390_pv_destroy_vm(kvm, &cmd->rc, &cmd->rrc);
+ if (!r)
+ kvm_s390_pv_dealloc_vm(kvm);
+ break;
+ }
+ case KVM_PV_VM_SET_SEC_PARMS: {
+ struct kvm_s390_pv_sec_parm parms = {};
+ void *hdr;
+
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm))
+ break;
+
+ r = -EFAULT;
+ if (copy_from_user(&parms, argp, sizeof(parms)))
+ break;
+
+ /* Currently restricted to 8KB */
+ r = -EINVAL;
+ if (parms.length > PAGE_SIZE * 2)
+ break;
+
+ r = -ENOMEM;
+ hdr = vmalloc(parms.length);
+ if (!hdr)
+ break;
+
+ r = -EFAULT;
+ if (!copy_from_user(hdr, (void __user *)parms.origin,
+ parms.length))
+ r = kvm_s390_pv_set_sec_parms(kvm, hdr, parms.length,
+ &cmd->rc, &cmd->rrc);
+
+ vfree(hdr);
+ break;
+ }
+ case KVM_PV_VM_UNPACK: {
+ struct kvm_s390_pv_unp unp = {};
+
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm))
+ break;
+
+ r = -EFAULT;
+ if (copy_from_user(&unp, argp, sizeof(unp)))
+ break;
+
+ r = kvm_s390_pv_unpack(kvm, unp.addr, unp.size, unp.tweak,
+ &cmd->rc, &cmd->rrc);
+ break;
+ }
+ case KVM_PV_VM_VERIFY: {
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm))
+ break;
+
+ r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+ UVC_CMD_VERIFY_IMG, &cmd->rc, &cmd->rrc);
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT VERIFY: rc %x rrc %x", cmd->rc,
+ cmd->rrc);
+ break;
+ }
+ default:
+ return -ENOTTY;
+ }
+ return r;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2262,6 +2402,27 @@ long kvm_arch_vm_ioctl(struct file *filp,
mutex_unlock(&kvm->slots_lock);
break;
}
+ case KVM_S390_PV_COMMAND: {
+ struct kvm_pv_cmd args;
+
+ r = 0;
+ if (!is_prot_virt_host()) {
+ r = -EINVAL;
+ break;
+ }
+ if (copy_from_user(&args, argp, sizeof(args))) {
+ r = -EFAULT;
+ break;
+ }
+ mutex_lock(&kvm->lock);
+ r = kvm_s390_handle_pv(kvm, &args);
+ mutex_unlock(&kvm->lock);
+ if (copy_to_user(argp, &args, sizeof(args))) {
+ r = -EFAULT;
+ break;
+ }
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -2525,6 +2686,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
+ u16 rc, rrc;
+
VCPU_EVENT(vcpu, 3, "%s", "free cpu");
trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
kvm_s390_clear_local_irqs(vcpu);
@@ -2537,6 +2700,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
if (vcpu->kvm->arch.use_cmma)
kvm_s390_vcpu_unsetup_cmma(vcpu);
+ /* We can not hold the vcpu mutex here, we are already dying */
+ if (kvm_s390_pv_cpu_get_handle(vcpu))
+ kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc);
free_page((unsigned long)(vcpu->arch.sie_block));
}
@@ -2558,10 +2724,21 @@ static void kvm_free_vcpus(struct kvm *kvm)
void kvm_arch_destroy_vm(struct kvm *kvm)
{
+ u16 rc, rrc;
kvm_free_vcpus(kvm);
sca_dispose(kvm);
- debug_unregister(kvm->arch.dbf);
kvm_s390_gisa_destroy(kvm);
+ /*
+ * We are already at the end of life and kvm->lock is not taken.
+ * This is ok as the file descriptor is closed by now and nobody
+ * can mess with the pv state. To avoid lockdep_assert_held from
+ * complaining we do not use kvm_s390_pv_is_protected.
+ */
+ if (kvm_s390_pv_get_handle(kvm)) {
+ kvm_s390_pv_destroy_vm(kvm, &rc, &rrc);
+ kvm_s390_pv_dealloc_vm(kvm);
+ }
+ debug_unregister(kvm->arch.dbf);
free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
gmap_remove(kvm->arch.gmap);
@@ -2657,6 +2834,9 @@ static int sca_switch_to_extended(struct kvm *kvm)
unsigned int vcpu_idx;
u32 scaol, scaoh;
+ if (kvm->arch.use_esca)
+ return 0;
+
new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
if (!new_sca)
return -ENOMEM;
@@ -2908,6 +3088,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
{
int rc = 0;
+ u16 uvrc, uvrrc;
atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
CPUSTAT_SM |
@@ -2975,6 +3156,11 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
kvm_s390_vcpu_crypto_setup(vcpu);
+ mutex_lock(&vcpu->kvm->lock);
+ if (kvm_s390_pv_is_protected(vcpu->kvm))
+ rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc);
+ mutex_unlock(&vcpu->kvm->lock);
+
return rc;
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 83dabb18e4d9..d62de29b2d6c 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -15,6 +15,7 @@
#include <linux/hrtimer.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <linux/lockdep.h>
#include <asm/facility.h>
#include <asm/processor.h>
#include <asm/sclp.h>
@@ -207,6 +208,40 @@ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
return kvm->arch.user_cpu_state_ctrl != 0;
}
+/* implemented in pv.c */
+void kvm_s390_pv_dealloc_vm(struct kvm *kvm);
+int kvm_s390_pv_alloc_vm(struct kvm *kvm);
+int kvm_s390_pv_create_vm(struct kvm *kvm, u16 *rc, u16 *rrc);
+int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
+int kvm_s390_pv_destroy_vm(struct kvm *kvm, u16 *rc, u16 *rrc);
+void kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
+int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc,
+ u16 *rrc);
+int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
+ unsigned long tweak, u16 *rc, u16 *rrc);
+
+static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm)
+{
+ return kvm->arch.pv.handle;
+}
+
+static inline u64 kvm_s390_pv_cpu_get_handle(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.pv.handle;
+}
+
+static inline bool kvm_s390_pv_is_protected(struct kvm *kvm)
+{
+ lockdep_assert_held(&kvm->lock);
+ return !!kvm_s390_pv_get_handle(kvm);
+}
+
+static inline bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu)
+{
+ lockdep_assert_held(&vcpu->mutex);
+ return !!kvm_s390_pv_cpu_get_handle(vcpu);
+}
+
/* implemented in interrupt.c */
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
new file mode 100644
index 000000000000..67ea9a18ed8f
--- /dev/null
+++ b/arch/s390/kvm/pv.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hosting Secure Execution virtual machines
+ *
+ * Copyright IBM Corp. 2019
+ * Author(s): Janosch Frank <frankja@linux.ibm.com>
+ */
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/pagemap.h>
+#include <linux/sched/signal.h>
+#include <asm/pgalloc.h>
+#include <asm/gmap.h>
+#include <asm/uv.h>
+#include <asm/gmap.h>
+#include <asm/mman.h>
+#include "kvm-s390.h"
+
+void kvm_s390_pv_dealloc_vm(struct kvm *kvm)
+{
+ vfree(kvm->arch.pv.stor_var);
+ free_pages(kvm->arch.pv.stor_base,
+ get_order(uv_info.guest_base_stor_len));
+ memset(&kvm->arch.pv, 0, sizeof(kvm->arch.pv));
+}
+
+int kvm_s390_pv_alloc_vm(struct kvm *kvm)
+{
+ unsigned long base = uv_info.guest_base_stor_len;
+ unsigned long virt = uv_info.guest_virt_var_stor_len;
+ unsigned long npages = 0, vlen = 0;
+ struct kvm_memory_slot *memslot;
+
+ kvm->arch.pv.stor_var = NULL;
+ kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, get_order(base));
+ if (!kvm->arch.pv.stor_base)
+ return -ENOMEM;
+
+ /*
+ * Calculate current guest storage for allocation of the
+ * variable storage, which is based on the length in MB.
+ *
+ * Slots are sorted by GFN
+ */
+ mutex_lock(&kvm->slots_lock);
+ memslot = kvm_memslots(kvm)->memslots;
+ npages = memslot->base_gfn + memslot->npages;
+ mutex_unlock(&kvm->slots_lock);
+
+ kvm->arch.pv.guest_len = npages * PAGE_SIZE;
+
+ /* Allocate variable storage */
+ vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE);
+ vlen += uv_info.guest_virt_base_stor_len;
+ kvm->arch.pv.stor_var = vzalloc(vlen);
+ if (!kvm->arch.pv.stor_var)
+ goto out_err;
+ return 0;
+
+out_err:
+ kvm_s390_pv_dealloc_vm(kvm);
+ return -ENOMEM;
+}
+
+int kvm_s390_pv_destroy_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+ int cc;
+
+ cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+ UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
+ WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
+ atomic_set(&kvm->mm->context.is_protected, 0);
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc);
+ return cc;
+}
+
+void kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
+{
+ int cc = 0;
+
+ if (kvm_s390_pv_cpu_get_handle(vcpu)) {
+ cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
+ UVC_CMD_DESTROY_SEC_CPU, rc, rrc);
+
+ KVM_UV_EVENT(vcpu->kvm, 3,
+ "PROTVIRT DESTROY VCPU %d: rc %x rrc %x",
+ vcpu->vcpu_id, *rc, *rrc);
+ WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x",
+ *rc, *rrc);
+ }
+
+ free_pages(vcpu->arch.pv.stor_base,
+ get_order(uv_info.guest_cpu_stor_len));
+ vcpu->arch.sie_block->pv_handle_cpu = 0;
+ vcpu->arch.sie_block->pv_handle_config = 0;
+ memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv));
+ vcpu->arch.sie_block->sdf = 0;
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+}
+
+int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
+{
+ struct uv_cb_csc uvcb = {
+ .header.cmd = UVC_CMD_CREATE_SEC_CPU,
+ .header.len = sizeof(uvcb),
+ };
+ int cc;
+
+ if (kvm_s390_pv_cpu_get_handle(vcpu))
+ return -EINVAL;
+
+ vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL,
+ get_order(uv_info.guest_cpu_stor_len));
+ if (!vcpu->arch.pv.stor_base)
+ return -ENOMEM;
+
+ /* Input */
+ uvcb.guest_handle = kvm_s390_pv_get_handle(vcpu->kvm);
+ uvcb.num = vcpu->arch.sie_block->icpua;
+ uvcb.state_origin = (u64)vcpu->arch.sie_block;
+ uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base;
+
+ cc = uv_call(0, (u64)&uvcb);
+ *rc = uvcb.header.rc;
+ *rrc = uvcb.header.rrc;
+ KVM_UV_EVENT(vcpu->kvm, 3,
+ "PROTVIRT CREATE VCPU: cpu %d handle %llx rc %x rrc %x",
+ vcpu->vcpu_id, uvcb.cpu_handle, uvcb.header.rc,
+ uvcb.header.rrc);
+
+ if (cc) {
+ u16 dummy;
+
+ kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy);
+ return -EINVAL;
+ }
+
+ /* Output */
+ vcpu->arch.pv.handle = uvcb.cpu_handle;
+ vcpu->arch.sie_block->pv_handle_cpu = uvcb.cpu_handle;
+ vcpu->arch.sie_block->pv_handle_config = kvm_s390_pv_get_handle(vcpu->kvm);
+ vcpu->arch.sie_block->sdf = 2;
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ return 0;
+}
+
+int kvm_s390_pv_create_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+ u16 drc, drrc;
+ int cc;
+
+ struct uv_cb_cgc uvcb = {
+ .header.cmd = UVC_CMD_CREATE_SEC_CONF,
+ .header.len = sizeof(uvcb)
+ };
+
+ /* Inputs */
+ uvcb.guest_stor_origin = 0; /* MSO is 0 for KVM */
+ uvcb.guest_stor_len = kvm->arch.pv.guest_len;
+ uvcb.guest_asce = kvm->arch.gmap->asce;
+ uvcb.guest_sca = (unsigned long)kvm->arch.sca;
+ uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base;
+ uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var;
+
+ cc = uv_call(0, (u64)&uvcb);
+ *rc = uvcb.header.rc;
+ *rrc = uvcb.header.rrc;
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x",
+ uvcb.guest_handle, uvcb.guest_stor_len, *rc, *rrc);
+
+ /* Outputs */
+ kvm->arch.pv.handle = uvcb.guest_handle;
+
+ if (cc && (uvcb.header.rc & UVC_RC_NEED_DESTROY)) {
+ kvm_s390_pv_destroy_vm(kvm, &drc, &drrc);
+ return -EINVAL;
+ }
+ kvm->arch.gmap->guest_handle = uvcb.guest_handle;
+ atomic_set(&kvm->mm->context.is_protected, 1);
+ return cc;
+}
+
+int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc,
+ u16 *rrc)
+{
+ struct uv_cb_ssc uvcb = {
+ .header.cmd = UVC_CMD_SET_SEC_CONF_PARAMS,
+ .header.len = sizeof(uvcb),
+ .sec_header_origin = (u64)hdr,
+ .sec_header_len = length,
+ .guest_handle = kvm_s390_pv_get_handle(kvm),
+ };
+ int cc;
+
+ cc = uv_call(0, (u64)&uvcb);
+ *rc = uvcb.header.rc;
+ *rrc = uvcb.header.rrc;
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x",
+ *rc, *rrc);
+ if (cc)
+ return -EINVAL;
+ return 0;
+}
+
+static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak[2],
+ u16 *rc, u16 *rrc)
+{
+ struct uv_cb_unp uvcb = {
+ .header.cmd = UVC_CMD_UNPACK_IMG,
+ .header.len = sizeof(uvcb),
+ .guest_handle = kvm_s390_pv_get_handle(kvm),
+ .gaddr = addr,
+ .tweak[0] = tweak[0],
+ .tweak[1] = tweak[1],
+ };
+ int ret;
+
+ ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb);
+ *rc = uvcb.header.rc;
+ *rrc = uvcb.header.rrc;
+
+ if (ret && ret != -EAGAIN)
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x",
+ uvcb.gaddr, *rc, *rrc);
+ return ret;
+}
+
+int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
+ unsigned long tweak, u16 *rc, u16 *rrc)
+{
+ u64 tw[2] = {tweak, 0};
+ int ret = 0;
+
+ if (addr & ~PAGE_MASK || !size || size & ~PAGE_MASK)
+ return -EINVAL;
+
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx",
+ addr, size);
+
+ while (tw[1] < size) {
+ ret = unpack_one(kvm, addr, tw, rc, rrc);
+ if (ret == -EAGAIN) {
+ cond_resched();
+ if (fatal_signal_pending(current))
+ break;
+ continue;
+ }
+ if (ret)
+ break;
+ addr += PAGE_SIZE;
+ tw[1] += PAGE_SIZE;
+ }
+ if (!ret)
+ KVM_UV_EVENT(kvm, 3, "%s", "PROTVIRT VM UNPACK: successful");
+ return ret;
+}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 4b95f9a31a2f..efb5c4d65396 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1478,6 +1478,37 @@ struct kvm_enc_region {
#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
+struct kvm_s390_pv_sec_parm {
+ __u64 origin;
+ __u64 length;
+};
+
+struct kvm_s390_pv_unp {
+ __u64 addr;
+ __u64 size;
+ __u64 tweak;
+};
+
+enum pv_cmd_id {
+ KVM_PV_ENABLE,
+ KVM_PV_DISABLE,
+ KVM_PV_VM_SET_SEC_PARMS,
+ KVM_PV_VM_UNPACK,
+ KVM_PV_VM_VERIFY,
+};
+
+struct kvm_pv_cmd {
+ __u32 cmd; /* Command to be executed */
+ __u16 rc; /* Ultravisor return code */
+ __u16 rrc; /* Ultravisor return reason code */
+ __u64 data; /* Data or address */
+ __u32 flags; /* flags for future extensions. Must be 0 for now */
+ __u32 reserved[3];
+};
+
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
--
2.25.0
^ permalink raw reply related
* [PATCH v3 23/37] KVM: s390: protvirt: STSI handling
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
Save response to sidad and disable address checking for protected
guests.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/priv.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ed52ffa8d5d4..394b57090ff6 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -872,7 +872,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
operand2 = kvm_s390_get_base_disp_s(vcpu, &ar);
- if (operand2 & 0xfff)
+ if (!kvm_s390_pv_cpu_is_protected(vcpu) && (operand2 & 0xfff))
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
switch (fc) {
@@ -893,8 +893,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
handle_stsi_3_2_2(vcpu, (void *) mem);
break;
}
-
- rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ memcpy((void *)sida_origin(vcpu->arch.sie_block), (void *)mem,
+ PAGE_SIZE);
+ rc = 0;
+ } else {
+ rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE);
+ }
if (rc) {
rc = kvm_s390_inject_prog_cond(vcpu, rc);
goto out;
--
2.25.0
^ permalink raw reply related
* [PATCH v3 32/37] KVM: s390: protvirt: do not inject interrupts after start
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
As PSW restart is handled by the ultravisor (and we only get a start
notification) we must re-check the PSW after a start before injecting
interrupts.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
arch/s390/kvm/kvm-s390.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4503f153efd7..76ab9e4c8f55 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4479,6 +4479,13 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
if (kvm_s390_pv_cpu_is_protected(vcpu))
r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR);
kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED);
+ /*
+ * The real PSW might have changed due to a RESTART interpreted by the
+ * ultravisor. We block all interrupts and let the next sie exit
+ * refresh our view.
+ */
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK;
/*
* Another VCPU might have used IBS while we were offline.
* Let's play safe and flush the VCPU at startup.
--
2.25.0
^ permalink raw reply related
* [PATCH v3 20/37] KVM: s390: protvirt: handle secure guest prefix pages
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
The SPX instruction is handled by the ultravisor. We do get a
notification intercept, though. Let us update our internal view.
In addition to that, when the guest prefix page is not secure, an
intercept 112 (0x70) is indicated. Let us make the prefix pages
secure again.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/kvm_host.h | 1 +
arch/s390/kvm/intercept.c | 18 ++++++++++++++++++
2 files changed, 19 insertions(+)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index aa945b101fff..0ea82152d2f7 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -225,6 +225,7 @@ struct kvm_s390_sie_block {
#define ICPT_INT_ENABLE 0x64
#define ICPT_PV_INSTR 0x68
#define ICPT_PV_NOTIFY 0x6c
+#define ICPT_PV_PREF 0x70
__u8 icptcode; /* 0x0050 */
__u8 icptstatus; /* 0x0051 */
__u16 ihcpu; /* 0x0052 */
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index cf4c0da4e956..f4d533554157 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -451,6 +451,15 @@ static int handle_operexc(struct kvm_vcpu *vcpu)
return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
}
+static int handle_pv_spx(struct kvm_vcpu *vcpu)
+{
+ u32 pref = *(u32 *)vcpu->arch.sie_block->sidad;
+
+ kvm_s390_set_prefix(vcpu, pref);
+ trace_kvm_s390_handle_prefix(vcpu, 1, pref);
+ return 0;
+}
+
static int handle_pv_sclp(struct kvm_vcpu *vcpu)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
@@ -477,6 +486,8 @@ static int handle_pv_sclp(struct kvm_vcpu *vcpu)
static int handle_pv_notification(struct kvm_vcpu *vcpu)
{
+ if (vcpu->arch.sie_block->ipa == 0xb210)
+ return handle_pv_spx(vcpu);
if (vcpu->arch.sie_block->ipa == 0xb220)
return handle_pv_sclp(vcpu);
@@ -534,6 +545,13 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
case ICPT_PV_NOTIFY:
rc = handle_pv_notification(vcpu);
break;
+ case ICPT_PV_PREF:
+ rc = 0;
+ gmap_convert_to_secure(vcpu->arch.gmap,
+ kvm_s390_get_prefix(vcpu));
+ gmap_convert_to_secure(vcpu->arch.gmap,
+ kvm_s390_get_prefix(vcpu) + PAGE_SIZE);
+ break;
default:
return -EOPNOTSUPP;
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 18/37] KVM: s390: protvirt: Add new gprs location handling
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
Guest registers for protected guests are stored at offset 0x380. We
will copy those to the usual places. Long term we could refactor this
or use register access functions.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/kvm_host.h | 4 +++-
arch/s390/kvm/kvm-s390.c | 11 +++++++++++
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index ba3364b37159..4fcbb055a565 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -343,7 +343,9 @@ struct kvm_s390_itdb {
struct sie_page {
struct kvm_s390_sie_block sie_block;
struct mcck_volatile_info mcck_info; /* 0x0200 */
- __u8 reserved218[1000]; /* 0x0218 */
+ __u8 reserved218[360]; /* 0x0218 */
+ __u64 pv_grregs[16]; /* 0x0380 */
+ __u8 reserved400[512]; /* 0x0400 */
struct kvm_s390_itdb itdb; /* 0x0600 */
__u8 reserved700[2304]; /* 0x0700 */
};
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f9e05b3f0289..4750f36dc16d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4035,6 +4035,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
static int __vcpu_run(struct kvm_vcpu *vcpu)
{
int rc, exit_reason;
+ struct sie_page *sie_page = (struct sie_page *)vcpu->arch.sie_block;
/*
* We try to hold kvm->srcu during most of vcpu_run (except when run-
@@ -4056,8 +4057,18 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
guest_enter_irqoff();
__disable_cpu_timer_accounting(vcpu);
local_irq_enable();
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ memcpy(sie_page->pv_grregs,
+ vcpu->run->s.regs.gprs,
+ sizeof(sie_page->pv_grregs));
+ }
exit_reason = sie64a(vcpu->arch.sie_block,
vcpu->run->s.regs.gprs);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ memcpy(vcpu->run->s.regs.gprs,
+ sie_page->pv_grregs,
+ sizeof(sie_page->pv_grregs));
+ }
local_irq_disable();
__enable_cpu_timer_accounting(vcpu);
guest_exit_irqoff();
--
2.25.0
^ permalink raw reply related
* [PATCH v3 27/37] KVM: s390: protvirt: Add program exception injection
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
Only two program exceptions can be injected for a protected guest:
specification and operand.
For both, a code needs to be specified in the interrupt injection
control of the state description, as the guest prefix page is not
accessible to KVM for such guests.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/interrupt.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index aaff3dbd669e..41b7faa8e5de 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -836,6 +836,21 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
return rc ? -EFAULT : 0;
}
+static int __deliver_prog_pv(struct kvm_vcpu *vcpu, u16 code)
+{
+ switch (code) {
+ case PGM_SPECIFICATION:
+ vcpu->arch.sie_block->iictl = IICTL_CODE_SPECIFICATION;
+ break;
+ case PGM_OPERAND:
+ vcpu->arch.sie_block->iictl = IICTL_CODE_OPERAND;
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -856,6 +871,10 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info.code, 0);
+ /* PER is handled by the ultravisor */
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ return __deliver_prog_pv(vcpu, pgm_info.code & ~PGM_PER);
+
switch (pgm_info.code & ~PGM_PER) {
case PGM_AFX_TRANSLATION:
case PGM_ASX_TRANSLATION:
--
2.25.0
^ permalink raw reply related
* [PATCH v3 07/37] KVM: s390: protvirt: Add UV debug trace
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
Let's have some debug traces which stay around for longer than the
guest.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/kvm-s390.c | 9 ++++++++-
arch/s390/kvm/kvm-s390.h | 11 +++++++++++
2 files changed, 19 insertions(+), 1 deletion(-)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d7ff30e45589..cc7793525a69 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -220,6 +220,7 @@ static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc;
static struct gmap_notifier gmap_notifier;
static struct gmap_notifier vsie_gmap_notifier;
debug_info_t *kvm_s390_dbf;
+debug_info_t *kvm_s390_dbf_uv;
/* Section: not file related */
int kvm_arch_hardware_enable(void)
@@ -460,7 +461,12 @@ int kvm_arch_init(void *opaque)
if (!kvm_s390_dbf)
return -ENOMEM;
- if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view))
+ kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long));
+ if (!kvm_s390_dbf_uv)
+ goto out;
+
+ if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) ||
+ debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view))
goto out;
kvm_s390_cpu_feat_init();
@@ -487,6 +493,7 @@ void kvm_arch_exit(void)
{
kvm_s390_gib_destroy();
debug_unregister(kvm_s390_dbf);
+ debug_unregister(kvm_s390_dbf_uv);
}
/* Section: device related */
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 6d9448dbd052..83dabb18e4d9 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -25,6 +25,17 @@
#define IS_ITDB_VALID(vcpu) ((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1))
extern debug_info_t *kvm_s390_dbf;
+extern debug_info_t *kvm_s390_dbf_uv;
+
+#define KVM_UV_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
+do { \
+ debug_sprintf_event((d_kvm)->arch.dbf, d_loglevel, d_string "\n", \
+ d_args); \
+ debug_sprintf_event(kvm_s390_dbf_uv, d_loglevel, \
+ "%d: " d_string "\n", (d_kvm)->userspace_pid, \
+ d_args); \
+} while (0)
+
#define KVM_EVENT(d_loglevel, d_string, d_args...)\
do { \
debug_sprintf_event(kvm_s390_dbf, d_loglevel, d_string "\n", \
--
2.25.0
^ permalink raw reply related
* [PATCH v3 25/37] KVM: s390: protvirt: Do only reset registers that are accessible
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
For protected VMs the hypervisor can not access guest breaking event
address, program parameter, bpbc and todpr. Do not reset those fields
as the control block does not provide access to these fields.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/kvm-s390.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 436778d3dc14..db28a717a622 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3478,14 +3478,16 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
kvm_s390_set_prefix(vcpu, 0);
kvm_s390_set_cpu_timer(vcpu, 0);
vcpu->arch.sie_block->ckc = 0;
- vcpu->arch.sie_block->todpr = 0;
memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr));
vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK;
vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK;
vcpu->run->s.regs.fpc = 0;
- vcpu->arch.sie_block->gbea = 1;
- vcpu->arch.sie_block->pp = 0;
- vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+ if (!kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->gbea = 1;
+ vcpu->arch.sie_block->pp = 0;
+ vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+ vcpu->arch.sie_block->todpr = 0;
+ }
}
static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
--
2.25.0
^ permalink raw reply related
* [PATCH v3 31/37] KVM: s390: protvirt: Mask PSW interrupt bits for interception 104 and 112
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
We're not allowed to inject interrupts on intercepts that leave the
guest state in an "in-between" state where the next SIE entry will do a
continuation, namely secure instruction interception (104) and secure
prefix interception (112).
As our PSW is just a copy of the real one that will be replaced on the
next exit, we can mask out the interrupt bits in the PSW to make sure
that we do not inject anything.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/kvm-s390.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f0b6609b65b6..4503f153efd7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4064,6 +4064,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
return vcpu_post_run_fault_in_sie(vcpu);
}
+#define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK)
static int __vcpu_run(struct kvm_vcpu *vcpu)
{
int rc, exit_reason;
@@ -4100,6 +4101,16 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
memcpy(vcpu->run->s.regs.gprs,
sie_page->pv_grregs,
sizeof(sie_page->pv_grregs));
+ /*
+ * We're not allowed to inject interrupts on intercepts
+ * that leave the guest state in an "in-between" state
+ * where the next SIE entry will do a continuation.
+ * Fence interrupts in our "internal" PSW.
+ */
+ if (vcpu->arch.sie_block->icptcode == ICPT_PV_INSTR ||
+ vcpu->arch.sie_block->icptcode == ICPT_PV_PREF) {
+ vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK;
+ }
}
local_irq_disable();
__enable_cpu_timer_accounting(vcpu);
--
2.25.0
^ permalink raw reply related
* [PATCH v3 10/37] KVM: s390: protvirt: Add KVM api documentation
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
Add documentation for KVM_CAP_S390_PROTECTED capability and the
KVM_S390_PV_COMMAND and KVM_S390_PV_COMMAND_VCPU ioctls.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
Documentation/virt/kvm/api.rst | 52 ++++++++++++++++++++++++++++++++++
1 file changed, 52 insertions(+)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 97a72a53fa4b..77e1edfe5d4c 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4646,6 +4646,51 @@ the clear cpu reset definition in the POP. However, the cpu is not put
into ESA mode. This reset is a superset of the initial reset.
+4.125 KVM_S390_PV_COMMAND
+-------------------------
+
+:Capability: KVM_CAP_S390_PROTECTED
+:Architectures: s390
+:Type: vm ioctl
+:Parameters: struct kvm_pv_cmd
+:Returns: 0 on success, < 0 on error
+
+::
+
+ struct kvm_pv_cmd {
+ __u32 cmd; /* Command to be executed */
+ __u16 rc; /* Ultravisor return code */
+ __u16 rrc; /* Ultravisor return reason code */
+ __u64 data; /* Data or address */
+ __u32 flags; /* flags for future extensions. Must be 0 for now */
+ __u32 reserved[3];
+ };
+
+cmd values:
+
+KVM_PV_ENABLE
+ Allocate memory and register the VM with the Ultravisor, thereby
+ donating memory to the Ultravisor making it inaccessible to KVM.
+ Also converts all existing CPUs to protected ones. Future hotplug
+ CPUs will become protected during creation.
+
+KVM_PV_DISABLE
+ Deregisters the VM from the Ultravisor and frees memory that was
+ donated, so the kernel can use it again. All registered VCPUs are
+ converted back to non-protected ones.
+
+KVM_PV_VM_SET_SEC_PARMS
+ Pass the image header from VM memory to the Ultravisor in
+ preparation of image unpacking and verification.
+
+KVM_PV_VM_UNPACK
+ Unpack (protect and decrypt) a page of the encrypted boot image.
+
+KVM_PV_VM_VERIFY
+ Verify the integrity of the unpacked image. Only if this succeeds,
+ KVM is allowed to start protected VCPUs.
+
+
5. The kvm_run structure
========================
@@ -6024,3 +6069,10 @@ Architectures: s390
This capability indicates that the KVM_S390_NORMAL_RESET and
KVM_S390_CLEAR_RESET ioctls are available.
+
+8.23 KVM_CAP_S390_PROTECTED
+
+Architecture: s390
+
+This capability indicates that KVM can start protected VMs and the
+Ultravisor has therefore been initialized.
--
2.25.0
^ permalink raw reply related
* [PATCH v3 03/37] s390/protvirt: introduce host side setup
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Vasily Gorbik <gor@linux.ibm.com>
Add "prot_virt" command line option which controls if the kernel
protected VMs support is enabled at early boot time. This has to be
done early, because it needs large amounts of memory and will disable
some features like STP time sync for the lpar.
Extend ultravisor info definitions and expose it via uv_info struct
filled in during startup.
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
.../admin-guide/kernel-parameters.txt | 5 ++
arch/s390/boot/Makefile | 2 +-
arch/s390/boot/uv.c | 21 +++++++-
arch/s390/include/asm/uv.h | 46 +++++++++++++++-
arch/s390/kernel/Makefile | 1 +
arch/s390/kernel/setup.c | 4 --
arch/s390/kernel/uv.c | 52 +++++++++++++++++++
7 files changed, 123 insertions(+), 8 deletions(-)
create mode 100644 arch/s390/kernel/uv.c
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index dbc22d684627..b0beae9b9e36 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3795,6 +3795,11 @@
before loading.
See Documentation/admin-guide/blockdev/ramdisk.rst.
+ prot_virt= [S390] enable hosting protected virtual machines
+ isolated from the hypervisor (if hardware supports
+ that).
+ Format: <bool>
+
psi= [KNL] Enable or disable pressure stall information
tracking.
Format: <bool>
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index e2c47d3a1c89..30f1811540c5 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -37,7 +37,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o
obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
obj-y += version.o pgm_check_info.o ctype.o text_dma.o
-obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o
+obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o
obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o
obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
targets := bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y)
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
index 3f501159ee9f..eeb121108242 100644
--- a/arch/s390/boot/uv.c
+++ b/arch/s390/boot/uv.c
@@ -3,7 +3,13 @@
#include <asm/facility.h>
#include <asm/sections.h>
+/* will be used in arch/s390/kernel/uv.c */
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
int __bootdata_preserved(prot_virt_guest);
+#endif
+#if IS_ENABLED(CONFIG_KVM)
+struct uv_info __bootdata_preserved(uv_info);
+#endif
void uv_query_info(void)
{
@@ -19,7 +25,20 @@ void uv_query_info(void)
if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100)
return;
- if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
+ if (IS_ENABLED(CONFIG_KVM)) {
+ memcpy(uv_info.inst_calls_list, uvcb.inst_calls_list, sizeof(uv_info.inst_calls_list));
+ uv_info.uv_base_stor_len = uvcb.uv_base_stor_len;
+ uv_info.guest_base_stor_len = uvcb.conf_base_phys_stor_len;
+ uv_info.guest_virt_base_stor_len = uvcb.conf_base_virt_stor_len;
+ uv_info.guest_virt_var_stor_len = uvcb.conf_virt_var_stor_len;
+ uv_info.guest_cpu_stor_len = uvcb.cpu_stor_len;
+ uv_info.max_sec_stor_addr = ALIGN(uvcb.max_guest_stor_addr, PAGE_SIZE);
+ uv_info.max_num_sec_conf = uvcb.max_num_sec_conf;
+ uv_info.max_guest_cpus = uvcb.max_guest_cpus;
+ }
+
+ if (IS_ENABLED(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) &&
+ test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
test_bit_inv(BIT_UVC_CMD_REMOVE_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list))
prot_virt_guest = 1;
}
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 4093a2856929..422aee15c9cc 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -44,7 +44,19 @@ struct uv_cb_qui {
struct uv_cb_header header;
u64 reserved08;
u64 inst_calls_list[4];
- u64 reserved30[15];
+ u64 reserved30[2];
+ u64 uv_base_stor_len;
+ u64 reserved48;
+ u64 conf_base_phys_stor_len;
+ u64 conf_base_virt_stor_len;
+ u64 conf_virt_var_stor_len;
+ u64 cpu_stor_len;
+ u32 reserved70[3];
+ u32 max_num_sec_conf;
+ u64 max_guest_stor_addr;
+ u8 reserved88[158 - 136];
+ u16 max_guest_cpus;
+ u8 reserveda0[200 - 160];
} __packed __aligned(8);
struct uv_cb_share {
@@ -69,6 +81,20 @@ static inline int uv_call(unsigned long r1, unsigned long r2)
return cc;
}
+struct uv_info {
+ unsigned long inst_calls_list[4];
+ unsigned long uv_base_stor_len;
+ unsigned long guest_base_stor_len;
+ unsigned long guest_virt_base_stor_len;
+ unsigned long guest_virt_var_stor_len;
+ unsigned long guest_cpu_stor_len;
+ unsigned long max_sec_stor_addr;
+ unsigned int max_num_sec_conf;
+ unsigned short max_guest_cpus;
+};
+
+extern struct uv_info uv_info;
+
#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
extern int prot_virt_guest;
@@ -121,11 +147,27 @@ static inline int uv_remove_shared(unsigned long addr)
return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS);
}
-void uv_query_info(void);
#else
#define is_prot_virt_guest() 0
static inline int uv_set_shared(unsigned long addr) { return 0; }
static inline int uv_remove_shared(unsigned long addr) { return 0; }
+#endif
+
+#if IS_ENABLED(CONFIG_KVM)
+extern int prot_virt_host;
+
+static inline int is_prot_virt_host(void)
+{
+ return prot_virt_host;
+}
+#else
+#define is_prot_virt_host() 0
+#endif
+
+#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || \
+ IS_ENABLED(CONFIG_KVM)
+void uv_query_info(void);
+#else
static inline void uv_query_info(void) {}
#endif
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2b1203cf7be6..22bfb8d5084e 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -78,6 +78,7 @@ obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o
obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_diag.o
obj-$(CONFIG_TRACEPOINTS) += trace.o
+obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o
# vdso
obj-y += vdso64/
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index b2c2f75860e8..a2496382175e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -92,10 +92,6 @@ char elf_platform[ELF_PLATFORM_SIZE];
unsigned long int_hwcap = 0;
-#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
-int __bootdata_preserved(prot_virt_guest);
-#endif
-
int __bootdata(noexec_disabled);
int __bootdata(memory_end_set);
unsigned long __bootdata(memory_end);
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
new file mode 100644
index 000000000000..b1f936710360
--- /dev/null
+++ b/arch/s390/kernel/uv.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common Ultravisor functions and initialization
+ *
+ * Copyright IBM Corp. 2019, 2020
+ */
+#define KMSG_COMPONENT "prot_virt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/sizes.h>
+#include <linux/bitmap.h>
+#include <linux/memblock.h>
+#include <asm/facility.h>
+#include <asm/sections.h>
+#include <asm/uv.h>
+
+/* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
+int __bootdata_preserved(prot_virt_guest);
+#endif
+
+#if IS_ENABLED(CONFIG_KVM)
+int prot_virt_host;
+EXPORT_SYMBOL(prot_virt_host);
+struct uv_info __bootdata_preserved(uv_info);
+EXPORT_SYMBOL(uv_info);
+
+static int __init prot_virt_setup(char *val)
+{
+ bool enabled;
+ int rc;
+
+ rc = kstrtobool(val, &enabled);
+ if (!rc && enabled)
+ prot_virt_host = 1;
+
+ if (is_prot_virt_guest() && prot_virt_host) {
+ prot_virt_host = 0;
+ pr_warn("Protected virtualization not available in protected guests.");
+ }
+
+ if (prot_virt_host && !test_facility(158)) {
+ prot_virt_host = 0;
+ pr_warn("Protected virtualization not supported by the hardware.");
+ }
+
+ return rc;
+}
+early_param("prot_virt", prot_virt_setup);
+#endif
--
2.25.0
^ permalink raw reply related
* [PATCH v3 15/37] KVM: s390: protvirt: Implement interrupt injection
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Michael Mueller <mimu@linux.ibm.com>
This defines the necessary data structures in the SIE control block to
inject machine checks,external and I/O interrupts. We first define the
the interrupt injection control, which defines the next interrupt to
inject. Then we define the fields that contain the payload for machine
checks,external and I/O interrupts.
This is then used to implement interruption injection for the following
list of interruption types:
- I/O (uses inject io interruption)
__deliver_io
- External (uses inject external interruption)
__deliver_cpu_timer
__deliver_ckc
__deliver_emergency_signal
__deliver_external_call
- cpu restart (uses inject restart interruption)
__deliver_restart
- machine checks (uses mcic, failing address and external damage)
__write_machine_check
Please note that posted interrupts (GISA) are not used for protected
guests as of today.
The service interrupt is handled in a followup patch.
Signed-off-by: Michael Mueller <mimu@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/kvm_host.h | 62 +++++++++++++----
arch/s390/kvm/interrupt.c | 115 +++++++++++++++++++++++--------
2 files changed, 138 insertions(+), 39 deletions(-)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index c6694f47b73b..a13dc77f8b07 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -222,7 +222,15 @@ struct kvm_s390_sie_block {
__u8 icptcode; /* 0x0050 */
__u8 icptstatus; /* 0x0051 */
__u16 ihcpu; /* 0x0052 */
- __u8 reserved54[2]; /* 0x0054 */
+ __u8 reserved54; /* 0x0054 */
+#define IICTL_CODE_NONE 0x00
+#define IICTL_CODE_MCHK 0x01
+#define IICTL_CODE_EXT 0x02
+#define IICTL_CODE_IO 0x03
+#define IICTL_CODE_RESTART 0x04
+#define IICTL_CODE_SPECIFICATION 0x10
+#define IICTL_CODE_OPERAND 0x11
+ __u8 iictl; /* 0x0055 */
__u16 ipa; /* 0x0056 */
__u32 ipb; /* 0x0058 */
__u32 scaoh; /* 0x005c */
@@ -259,24 +267,48 @@ struct kvm_s390_sie_block {
#define HPID_KVM 0x4
#define HPID_VSIE 0x5
__u8 hpid; /* 0x00b8 */
- __u8 reservedb9[11]; /* 0x00b9 */
- __u16 extcpuaddr; /* 0x00c4 */
- __u16 eic; /* 0x00c6 */
+ __u8 reservedb9[7]; /* 0x00b9 */
+ union {
+ struct {
+ __u32 eiparams; /* 0x00c0 */
+ __u16 extcpuaddr; /* 0x00c4 */
+ __u16 eic; /* 0x00c6 */
+ };
+ __u64 mcic; /* 0x00c0 */
+ } __packed;
__u32 reservedc8; /* 0x00c8 */
- __u16 pgmilc; /* 0x00cc */
- __u16 iprcc; /* 0x00ce */
- __u32 dxc; /* 0x00d0 */
- __u16 mcn; /* 0x00d4 */
- __u8 perc; /* 0x00d6 */
- __u8 peratmid; /* 0x00d7 */
+ union {
+ struct {
+ __u16 pgmilc; /* 0x00cc */
+ __u16 iprcc; /* 0x00ce */
+ };
+ __u32 edc; /* 0x00cc */
+ } __packed;
+ union {
+ struct {
+ __u32 dxc; /* 0x00d0 */
+ __u16 mcn; /* 0x00d4 */
+ __u8 perc; /* 0x00d6 */
+ __u8 peratmid; /* 0x00d7 */
+ };
+ __u64 faddr; /* 0x00d0 */
+ } __packed;
__u64 peraddr; /* 0x00d8 */
__u8 eai; /* 0x00e0 */
__u8 peraid; /* 0x00e1 */
__u8 oai; /* 0x00e2 */
__u8 armid; /* 0x00e3 */
__u8 reservede4[4]; /* 0x00e4 */
- __u64 tecmc; /* 0x00e8 */
- __u8 reservedf0[12]; /* 0x00f0 */
+ union {
+ __u64 tecmc; /* 0x00e8 */
+ struct {
+ __u16 subchannel_id; /* 0x00e8 */
+ __u16 subchannel_nr; /* 0x00ea */
+ __u32 io_int_parm; /* 0x00ec */
+ __u32 io_int_word; /* 0x00f0 */
+ };
+ } __packed;
+ __u8 reservedf4[8]; /* 0x00f4 */
#define CRYCB_FORMAT_MASK 0x00000003
#define CRYCB_FORMAT0 0x00000000
#define CRYCB_FORMAT1 0x00000001
@@ -546,6 +578,12 @@ enum irq_types {
#define IRQ_PEND_MCHK_MASK ((1UL << IRQ_PEND_MCHK_REP) | \
(1UL << IRQ_PEND_MCHK_EX))
+#define IRQ_PEND_EXT_II_MASK ((1UL << IRQ_PEND_EXT_CPU_TIMER) | \
+ (1UL << IRQ_PEND_EXT_CLOCK_COMP) | \
+ (1UL << IRQ_PEND_EXT_EMERGENCY) | \
+ (1UL << IRQ_PEND_EXT_EXTERNAL) | \
+ (1UL << IRQ_PEND_EXT_SERVICE))
+
struct kvm_s390_interrupt_info {
struct list_head list;
u64 type;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 0cebebf56515..61310b1f5b62 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -387,6 +387,12 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
__clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
if (psw_mchk_disabled(vcpu))
active_mask &= ~IRQ_PEND_MCHK_MASK;
+ /* PV guest cpus can have a single interruption injected at a time. */
+ if (kvm_s390_pv_cpu_is_protected(vcpu) &&
+ vcpu->arch.sie_block->iictl != IICTL_CODE_NONE)
+ active_mask &= ~(IRQ_PEND_EXT_II_MASK |
+ IRQ_PEND_IO_MASK |
+ IRQ_PEND_MCHK_MASK);
/*
* Check both floating and local interrupt's cr14 because
* bit IRQ_PEND_MCHK_REP could be set in both cases.
@@ -479,19 +485,23 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu)
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- int rc;
+ int rc = 0;
vcpu->stat.deliver_cputm++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
0, 0);
-
- rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
- (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_CPU_TIMER;
+ } else {
+ rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
+ (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ }
clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
@@ -499,19 +509,23 @@ static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- int rc;
+ int rc = 0;
vcpu->stat.deliver_ckc++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
0, 0);
-
- rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP,
- (u16 __user *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_CLK_COMP;
+ } else {
+ rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP,
+ (u16 __user *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ }
clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
@@ -553,6 +567,20 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
union mci mci;
int rc;
+ /*
+ * All other possible payload for a machine check (e.g. the register
+ * contents in the save area) will be handled by the ultravisor, as
+ * the hypervisor does not not have the needed information for
+ * protected guests.
+ */
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_MCHK;
+ vcpu->arch.sie_block->mcic = mchk->mcic;
+ vcpu->arch.sie_block->faddr = mchk->failing_storage_address;
+ vcpu->arch.sie_block->edc = mchk->ext_damage_code;
+ return 0;
+ }
+
mci.val = mchk->mcic;
/* take care of lazy register loading */
save_fpu_regs();
@@ -696,17 +724,21 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- int rc;
+ int rc = 0;
VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart");
vcpu->stat.deliver_restart_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
- rc = write_guest_lc(vcpu,
- offsetof(struct lowcore, restart_old_psw),
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_RESTART;
+ } else {
+ rc = write_guest_lc(vcpu,
+ offsetof(struct lowcore, restart_old_psw),
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ }
clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
@@ -748,6 +780,12 @@ static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
vcpu->stat.deliver_emergency_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
cpu_addr, 0);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_EMERGENCY_SIG;
+ vcpu->arch.sie_block->extcpuaddr = cpu_addr;
+ return 0;
+ }
rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
(u16 *)__LC_EXT_INT_CODE);
@@ -776,6 +814,12 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_INT_EXTERNAL_CALL,
extcall.code, 0);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_EXTERNAL_CALL;
+ vcpu->arch.sie_block->extcpuaddr = extcall.code;
+ return 0;
+ }
rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
(u16 *)__LC_EXT_INT_CODE);
@@ -1028,6 +1072,15 @@ static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io)
{
int rc;
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_IO;
+ vcpu->arch.sie_block->subchannel_id = io->subchannel_id;
+ vcpu->arch.sie_block->subchannel_nr = io->subchannel_nr;
+ vcpu->arch.sie_block->io_int_parm = io->io_int_parm;
+ vcpu->arch.sie_block->io_int_word = io->io_int_word;
+ return 0;
+ }
+
rc = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID);
rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR);
rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM);
@@ -1421,7 +1474,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
return -EINVAL;
- if (sclp.has_sigpif)
+ if (sclp.has_sigpif && !kvm_s390_pv_cpu_get_handle(vcpu))
return sca_inject_ext_call(vcpu, src_id);
if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
@@ -1773,7 +1826,14 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
kvm->stat.inject_io++;
isc = int_word_to_isc(inti->io.io_int_word);
- if (gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) {
+ /*
+ * Do not make use of gisa in protected mode. We do not use the lock
+ * checking variant as this is just a performance optimization and we
+ * do not hold the lock here. This is ok as the code will pick
+ * interrupts from both "lists" for delivery.
+ */
+ if (!kvm_s390_pv_get_handle(kvm) &&
+ gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) {
VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc);
gisa_set_ipm_gisc(gi->origin, isc);
kfree(inti);
@@ -1834,7 +1894,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type)
break;
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
if (!(type & KVM_S390_INT_IO_AI_MASK &&
- kvm->arch.gisa_int.origin))
+ kvm->arch.gisa_int.origin) ||
+ kvm_s390_pv_cpu_get_handle(dst_vcpu))
kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
break;
default:
--
2.25.0
^ permalink raw reply related
* [PATCH v3 35/37] s390: protvirt: Add sysfs firmware interface for Ultravisor information
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
That information, e.g. the maximum number of guests or installed
Ultravisor facilities, is interesting for QEMU, Libvirt and
administrators.
Let's provide an easily parsable API to get that information.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
arch/s390/kernel/uv.c | 86 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 86 insertions(+)
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 4539003dac9d..550e9617c459 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -323,5 +323,91 @@ int arch_make_page_accessible(struct page *page)
return rc;
}
EXPORT_SYMBOL_GPL(arch_make_page_accessible);
+#endif
+
+#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM)
+static ssize_t uv_query_facilities(struct kobject *kobj,
+ struct kobj_attribute *attr, char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n",
+ uv_info.inst_calls_list[0],
+ uv_info.inst_calls_list[1],
+ uv_info.inst_calls_list[2],
+ uv_info.inst_calls_list[3]);
+}
+
+static struct kobj_attribute uv_query_facilities_attr =
+ __ATTR(facilities, 0444, uv_query_facilities, NULL);
+
+static ssize_t uv_query_max_guest_cpus(struct kobject *kobj,
+ struct kobj_attribute *attr, char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%d\n",
+ uv_info.max_guest_cpus);
+}
+
+static struct kobj_attribute uv_query_max_guest_cpus_attr =
+ __ATTR(max_cpus, 0444, uv_query_max_guest_cpus, NULL);
+
+static ssize_t uv_query_max_guest_vms(struct kobject *kobj,
+ struct kobj_attribute *attr, char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%d\n",
+ uv_info.max_num_sec_conf);
+}
+
+static struct kobj_attribute uv_query_max_guest_vms_attr =
+ __ATTR(max_guests, 0444, uv_query_max_guest_vms, NULL);
+
+static ssize_t uv_query_max_guest_addr(struct kobject *kobj,
+ struct kobj_attribute *attr, char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%lx\n",
+ uv_info.max_sec_stor_addr);
+}
+
+static struct kobj_attribute uv_query_max_guest_addr_attr =
+ __ATTR(max_address, 0444, uv_query_max_guest_addr, NULL);
+
+static struct attribute *uv_query_attrs[] = {
+ &uv_query_facilities_attr.attr,
+ &uv_query_max_guest_cpus_attr.attr,
+ &uv_query_max_guest_vms_attr.attr,
+ &uv_query_max_guest_addr_attr.attr,
+ NULL,
+};
+
+static struct attribute_group uv_query_attr_group = {
+ .attrs = uv_query_attrs,
+};
+static struct kset *uv_query_kset;
+struct kobject *uv_kobj;
+
+static int __init uv_info_init(void)
+{
+ int rc = -ENOMEM;
+
+ if (!test_facility(158))
+ return 0;
+
+ uv_kobj = kobject_create_and_add("uv", firmware_kobj);
+ if (!uv_kobj)
+ return -ENOMEM;
+
+ uv_query_kset = kset_create_and_add("query", NULL, uv_kobj);
+ if (!uv_query_kset)
+ goto out_kobj;
+
+ rc = sysfs_create_group(&uv_query_kset->kobj, &uv_query_attr_group);
+ if (!rc)
+ return 0;
+
+ kset_unregister(uv_query_kset);
+out_kobj:
+ kobject_del(uv_kobj);
+ kobject_put(uv_kobj);
+ return rc;
+}
+device_initcall(uv_info_init);
#endif
--
2.25.0
^ permalink raw reply related
* [PATCH v3 30/37] KVM: s390: protvirt: Support cmd 5 operation state
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
Code 5 for the set cpu state UV call tells the UV to load a PSW from
the SE header (first IPL) or from guest location 0x0 (diag 308 subcode
0/1). Also it sets the cpu into operating state afterwards, so we can
start it.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/uv.h | 1 +
arch/s390/kvm/kvm-s390.c | 6 ++++++
2 files changed, 7 insertions(+)
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 99e1a14ef909..4945e44e1528 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -169,6 +169,7 @@ struct uv_cb_unp {
#define PV_CPU_STATE_OPR 1
#define PV_CPU_STATE_STP 2
#define PV_CPU_STATE_CHKSTP 3
+#define PV_CPU_STATE_OPR_LOAD 5
struct uv_cb_cpu_set_state {
struct uv_cb_header header;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 036bff58e75a..f0b6609b65b6 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3707,6 +3707,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
rc = kvm_s390_vcpu_start(vcpu);
break;
case KVM_MP_STATE_LOAD:
+ if (!kvm_s390_pv_cpu_is_protected(vcpu)) {
+ rc = -ENXIO;
+ break;
+ }
+ rc = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR_LOAD);
+ break;
case KVM_MP_STATE_CHECK_STOP:
/* fall through - CHECK_STOP and LOAD are not supported yet */
default:
--
2.25.0
^ permalink raw reply related
* [PATCH v3 33/37] KVM: s390: protvirt: Add UV cpu reset calls
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
For protected VMs, the VCPU resets are done by the Ultravisor, as KVM
has no access to the VCPU registers.
Note that the ultravisor will only accept a call for the exact reset
that has been requested.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/uv.h | 6 ++++++
arch/s390/kvm/kvm-s390.c | 20 ++++++++++++++++++++
2 files changed, 26 insertions(+)
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 4945e44e1528..cb95763ffb30 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -36,7 +36,10 @@
#define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300
#define UVC_CMD_UNPACK_IMG 0x0301
#define UVC_CMD_VERIFY_IMG 0x0302
+#define UVC_CMD_CPU_RESET 0x0310
+#define UVC_CMD_CPU_RESET_INITIAL 0x0311
#define UVC_CMD_PREPARE_RESET 0x0320
+#define UVC_CMD_CPU_RESET_CLEAR 0x0321
#define UVC_CMD_CPU_SET_STATE 0x0330
#define UVC_CMD_SET_UNSHARE_ALL 0x0340
#define UVC_CMD_PIN_PAGE_SHARED 0x0341
@@ -59,8 +62,11 @@ enum uv_cmds_inst {
BIT_UVC_CMD_SET_SEC_PARMS = 11,
BIT_UVC_CMD_UNPACK_IMG = 13,
BIT_UVC_CMD_VERIFY_IMG = 14,
+ BIT_UVC_CMD_CPU_RESET = 15,
+ BIT_UVC_CMD_CPU_RESET_INITIAL = 16,
BIT_UVC_CMD_CPU_SET_STATE = 17,
BIT_UVC_CMD_PREPARE_RESET = 18,
+ BIT_UVC_CMD_CPU_PERFORM_CLEAR_RESET = 19,
BIT_UVC_CMD_UNSHARE_ALL = 20,
BIT_UVC_CMD_PIN_PAGE_SHARED = 21,
BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22,
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 76ab9e4c8f55..d79ccd34b5cb 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4705,6 +4705,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
void __user *argp = (void __user *)arg;
int idx;
long r;
+ u16 rc, rrc;
vcpu_load(vcpu);
@@ -4726,14 +4727,33 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
case KVM_S390_CLEAR_RESET:
r = 0;
kvm_arch_vcpu_ioctl_clear_reset(vcpu);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
+ UVC_CMD_CPU_RESET_CLEAR, &rc, &rrc);
+ VCPU_EVENT(vcpu, 3, "PROTVIRT RESET CLEAR VCPU: rc %x rrc %x",
+ rc, rrc);
+ }
break;
case KVM_S390_INITIAL_RESET:
r = 0;
kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
+ UVC_CMD_CPU_RESET_INITIAL,
+ &rc, &rrc);
+ VCPU_EVENT(vcpu, 3, "PROTVIRT RESET INITIAL VCPU: rc %x rrc %x",
+ rc, rrc);
+ }
break;
case KVM_S390_NORMAL_RESET:
r = 0;
kvm_arch_vcpu_ioctl_normal_reset(vcpu);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
+ UVC_CMD_CPU_RESET, &rc, &rrc);
+ VCPU_EVENT(vcpu, 3, "PROTVIRT RESET NORMAL VCPU: rc %x rrc %x",
+ rc, rrc);
+ }
break;
case KVM_SET_ONE_REG:
case KVM_GET_ONE_REG: {
--
2.25.0
^ permalink raw reply related
* [PATCH v3 21/37] KVM: s390/mm: handle guest unpin events
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
The current code tries to first pin shared pages, if that fails (e.g.
because the page is not shared) it will export them. For shared pages
this means that we get a new intercept telling us that the guest is
unsharing that page. We will make the page secure at that point in time
and revoke the host access. This is synchronized with other host events,
e.g. the code will wait until host I/O has finished.
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/intercept.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index f4d533554157..850045034016 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -16,6 +16,7 @@
#include <asm/asm-offsets.h>
#include <asm/irq.h>
#include <asm/sysinfo.h>
+#include <asm/uv.h>
#include "kvm-s390.h"
#include "gaccess.h"
@@ -484,12 +485,35 @@ static int handle_pv_sclp(struct kvm_vcpu *vcpu)
return 0;
}
+static int handle_pv_uvc(struct kvm_vcpu *vcpu)
+{
+ struct uv_cb_share *guest_uvcb = (void *)vcpu->arch.sie_block->sidad;
+ struct uv_cb_cts uvcb = {
+ .header.cmd = UVC_CMD_UNPIN_PAGE_SHARED,
+ .header.len = sizeof(uvcb),
+ .guest_handle = kvm_s390_pv_get_handle(vcpu->kvm),
+ .gaddr = guest_uvcb->paddr,
+ };
+ int rc;
+
+ if (guest_uvcb->header.cmd != UVC_CMD_REMOVE_SHARED_ACCESS) {
+ WARN_ONCE(1, "Unexpected UVC 0x%x!\n", guest_uvcb->header.cmd);
+ return 0;
+ }
+ rc = gmap_make_secure(vcpu->arch.gmap, uvcb.gaddr, &uvcb);
+ if (rc == -EINVAL)
+ return 0;
+ return rc;
+}
+
static int handle_pv_notification(struct kvm_vcpu *vcpu)
{
if (vcpu->arch.sie_block->ipa == 0xb210)
return handle_pv_spx(vcpu);
if (vcpu->arch.sie_block->ipa == 0xb220)
return handle_pv_sclp(vcpu);
+ if (vcpu->arch.sie_block->ipa == 0xb9a4)
+ return handle_pv_uvc(vcpu);
return handle_instruction(vcpu);
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 24/37] KVM: s390: protvirt: disallow one_reg
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
A lot of the registers are controlled by the Ultravisor and never
visible to KVM. Some fields in the sie control block are overlayed, like
gbea. As no known userspace uses the ONE_REG interface on s390 if sync
regs are available, no functionality is lost if it is disabled for
protected guests.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
Documentation/virt/kvm/api.rst | 6 ++++--
arch/s390/kvm/kvm-s390.c | 3 +++
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 77e1edfe5d4c..58be7aba0db2 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -2117,7 +2117,8 @@ Errors:
====== ============================================================
ENOENT no such register
- EINVAL invalid register ID, or no such register
+ EINVAL invalid register ID, or no such register or used with VMs in
+ protected virtualization mode on s390
EPERM (arm64) register access not allowed before vcpu finalization
====== ============================================================
@@ -2552,7 +2553,8 @@ Errors include:
======== ============================================================
ENOENT no such register
- EINVAL invalid register ID, or no such register
+ EINVAL invalid register ID, or no such register or used with VMs in
+ protected virtualization mode on s390
EPERM (arm64) register access not allowed before vcpu finalization
======== ============================================================
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4f7d70157b2c..436778d3dc14 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4649,6 +4649,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
case KVM_SET_ONE_REG:
case KVM_GET_ONE_REG: {
struct kvm_one_reg reg;
+ r = -EINVAL;
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ break;
r = -EFAULT;
if (copy_from_user(®, argp, sizeof(reg)))
break;
--
2.25.0
^ permalink raw reply related
* [PATCH v3 22/37] KVM: s390: protvirt: Write sthyi data to instruction data area
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
STHYI data has to go through the bounce buffer.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/intercept.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 850045034016..a5de0e1975bb 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -392,7 +392,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
goto out;
}
- if (addr & ~PAGE_MASK)
+ if (!kvm_s390_pv_cpu_is_protected(vcpu) && (addr & ~PAGE_MASK))
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
sctns = (void *)get_zeroed_page(GFP_KERNEL);
@@ -403,10 +403,15 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
out:
if (!cc) {
- r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE);
- if (r) {
- free_page((unsigned long)sctns);
- return kvm_s390_inject_prog_cond(vcpu, r);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ memcpy((void *)(sida_origin(vcpu->arch.sie_block)),
+ sctns, PAGE_SIZE);
+ } else {
+ r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE);
+ if (r) {
+ free_page((unsigned long)sctns);
+ return kvm_s390_inject_prog_cond(vcpu, r);
+ }
}
}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 26/37] KVM: s390: protvirt: Only sync fmt4 registers
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
A lot of the registers are controlled by the Ultravisor and never
visible to KVM. Also some registers are overlayed, like gbea is with
sidad, which might leak data to userspace.
Hence we sync a minimal set of registers for both SIE formats and then
check and sync format 2 registers if necessary.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/kvm-s390.c | 110 +++++++++++++++++++++++++--------------
1 file changed, 70 insertions(+), 40 deletions(-)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index db28a717a622..303f994f3d03 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4084,7 +4084,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
return rc;
}
-static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void sync_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
struct runtime_instr_cb *riccb;
struct gs_cb *gscb;
@@ -4093,16 +4093,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
gscb = (struct gs_cb *) &kvm_run->s.regs.gscb;
vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
- if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
- kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
- if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
- memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
- /* some control register changes require a tlb flush */
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- }
if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
- kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
- vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea;
@@ -4143,6 +4134,36 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
}
+ if (MACHINE_HAS_GS) {
+ preempt_disable();
+ __ctl_set_bit(2, 4);
+ if (current->thread.gs_cb) {
+ vcpu->arch.host_gscb = current->thread.gs_cb;
+ save_gs_cb(vcpu->arch.host_gscb);
+ }
+ if (vcpu->arch.gs_enabled) {
+ current->thread.gs_cb = (struct gs_cb *)
+ &vcpu->run->s.regs.gscb;
+ restore_gs_cb(current->thread.gs_cb);
+ }
+ preempt_enable();
+ }
+ /* SIE will load etoken directly from SDNX and therefore kvm_run */
+}
+
+static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
+ kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+ if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
+ memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
+ /* some control register changes require a tlb flush */
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ }
+ if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
+ kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
+ vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
+ }
save_access_regs(vcpu->arch.host_acrs);
restore_access_regs(vcpu->run->s.regs.acrs);
/* save host (userspace) fprs/vrs */
@@ -4157,23 +4178,47 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if (test_fp_ctl(current->thread.fpu.fpc))
/* User space provided an invalid FPC, let's clear it */
current->thread.fpu.fpc = 0;
+
+ /* Sync fmt2 only data */
+ if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) {
+ sync_regs_fmt2(vcpu, kvm_run);
+ } else {
+ /*
+ * In several places we have to modify our internal view to
+ * not do things that are disallowed by the ultravisor. For
+ * example we must not inject interrupts after specific exits
+ * (e.g. 112 prefix page not secure). We do this by turning
+ * off the machine check, external and I/O interrupt bits
+ * of our PSW copy. To avoid getting validity intercepts, we
+ * do only accept the condition code from userspace.
+ */
+ vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_CC;
+ vcpu->arch.sie_block->gpsw.mask |= kvm_run->psw_mask &
+ PSW_MASK_CC;
+ }
+
+ kvm_run->kvm_dirty_regs = 0;
+}
+
+static void store_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
+ kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
+ kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
+ kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
if (MACHINE_HAS_GS) {
- preempt_disable();
__ctl_set_bit(2, 4);
- if (current->thread.gs_cb) {
- vcpu->arch.host_gscb = current->thread.gs_cb;
- save_gs_cb(vcpu->arch.host_gscb);
- }
- if (vcpu->arch.gs_enabled) {
- current->thread.gs_cb = (struct gs_cb *)
- &vcpu->run->s.regs.gscb;
- restore_gs_cb(current->thread.gs_cb);
- }
+ if (vcpu->arch.gs_enabled)
+ save_gs_cb(current->thread.gs_cb);
+ preempt_disable();
+ current->thread.gs_cb = vcpu->arch.host_gscb;
+ restore_gs_cb(vcpu->arch.host_gscb);
preempt_enable();
+ if (!vcpu->arch.host_gscb)
+ __ctl_clear_bit(2, 4);
+ vcpu->arch.host_gscb = NULL;
}
- /* SIE will load etoken directly from SDNX and therefore kvm_run */
-
- kvm_run->kvm_dirty_regs = 0;
+ /* SIE will save etoken directly into SDNX and therefore kvm_run */
}
static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -4184,13 +4229,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
- kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
- kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
- kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
kvm_run->s.regs.pft = vcpu->arch.pfault_token;
kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
- kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
save_access_regs(vcpu->run->s.regs.acrs);
restore_access_regs(vcpu->arch.host_acrs);
/* Save guest register state */
@@ -4199,19 +4240,8 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
/* Restore will be done lazily at return */
current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
- if (MACHINE_HAS_GS) {
- __ctl_set_bit(2, 4);
- if (vcpu->arch.gs_enabled)
- save_gs_cb(current->thread.gs_cb);
- preempt_disable();
- current->thread.gs_cb = vcpu->arch.host_gscb;
- restore_gs_cb(vcpu->arch.host_gscb);
- preempt_enable();
- if (!vcpu->arch.host_gscb)
- __ctl_clear_bit(2, 4);
- vcpu->arch.host_gscb = NULL;
- }
- /* SIE will save etoken directly into SDNX and therefore kvm_run */
+ if (likely(!kvm_s390_pv_cpu_is_protected(vcpu)))
+ store_regs_fmt2(vcpu, kvm_run);
}
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
--
2.25.0
^ permalink raw reply related
* [PATCH v3 36/37] KVM: s390: rstify new ioctls in api.rst
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
We also need to rstify the new ioctls that we added in parallel to the
rstification of the kvm docs.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
Documentation/virt/kvm/api.rst | 33 ++++++++++++++++++---------------
1 file changed, 18 insertions(+), 15 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 58be7aba0db2..faca9977cbe7 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4613,35 +4613,38 @@ unpins the VPA pages and releases all the device pages that are used to
track the secure pages by hypervisor.
4.122 KVM_S390_NORMAL_RESET
+---------------------------
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
This ioctl resets VCPU registers and control structures according to
the cpu reset definition in the POP (Principles Of Operation).
4.123 KVM_S390_INITIAL_RESET
+----------------------------
-Capability: none
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: none
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
This ioctl resets VCPU registers and control structures according to
the initial cpu reset definition in the POP. However, the cpu is not
put into ESA mode. This reset is a superset of the normal reset.
4.124 KVM_S390_CLEAR_RESET
+--------------------------
-Capability: KVM_CAP_S390_VCPU_RESETS
-Architectures: s390
-Type: vcpu ioctl
-Parameters: none
-Returns: 0
+:Capability: KVM_CAP_S390_VCPU_RESETS
+:Architectures: s390
+:Type: vcpu ioctl
+:Parameters: none
+:Returns: 0
This ioctl resets VCPU registers and control structures according to
the clear cpu reset definition in the POP. However, the cpu is not put
--
2.25.0
^ permalink raw reply related
* [PATCH v3 29/37] KVM: s390: protvirt: Report CPU state to Ultravisor
From: Christian Borntraeger @ 2020-02-20 10:40 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Janosch Frank <frankja@linux.ibm.com>
VCPU states have to be reported to the ultravisor for SIGP
interpretation, kdump, kexec and reboot.
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/uv.h | 15 +++++++++++++++
arch/s390/kvm/diag.c | 4 ++++
arch/s390/kvm/intercept.c | 4 ++++
arch/s390/kvm/kvm-s390.c | 33 ++++++++++++++++++++++-----------
arch/s390/kvm/kvm-s390.h | 5 +++--
arch/s390/kvm/pv.c | 18 ++++++++++++++++++
6 files changed, 66 insertions(+), 13 deletions(-)
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index a7595c647759..99e1a14ef909 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -37,6 +37,7 @@
#define UVC_CMD_UNPACK_IMG 0x0301
#define UVC_CMD_VERIFY_IMG 0x0302
#define UVC_CMD_PREPARE_RESET 0x0320
+#define UVC_CMD_CPU_SET_STATE 0x0330
#define UVC_CMD_SET_UNSHARE_ALL 0x0340
#define UVC_CMD_PIN_PAGE_SHARED 0x0341
#define UVC_CMD_UNPIN_PAGE_SHARED 0x0342
@@ -58,6 +59,7 @@ enum uv_cmds_inst {
BIT_UVC_CMD_SET_SEC_PARMS = 11,
BIT_UVC_CMD_UNPACK_IMG = 13,
BIT_UVC_CMD_VERIFY_IMG = 14,
+ BIT_UVC_CMD_CPU_SET_STATE = 17,
BIT_UVC_CMD_PREPARE_RESET = 18,
BIT_UVC_CMD_UNSHARE_ALL = 20,
BIT_UVC_CMD_PIN_PAGE_SHARED = 21,
@@ -164,6 +166,19 @@ struct uv_cb_unp {
u64 reserved38[3];
} __packed __aligned(8);
+#define PV_CPU_STATE_OPR 1
+#define PV_CPU_STATE_STP 2
+#define PV_CPU_STATE_CHKSTP 3
+
+struct uv_cb_cpu_set_state {
+ struct uv_cb_header header;
+ u64 reserved08[2];
+ u64 cpu_handle;
+ u8 reserved20[7];
+ u8 state;
+ u64 reserved28[5];
+};
+
/*
* A common UV call struct for calls that take no payload
* Examples:
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 3fb54ec2cf3e..130f0c51d162 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -201,6 +201,10 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
}
+ /*
+ * no need to check the return value of vcpu_stop as it can only have
+ * an error for protvirt, but protvirt means user cpu state
+ */
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
kvm_s390_vcpu_stop(vcpu);
vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index a5de0e1975bb..73cf2961ac4f 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -80,6 +80,10 @@ static int handle_stop(struct kvm_vcpu *vcpu)
return rc;
}
+ /*
+ * no need to check the return value of vcpu_stop as it can only have
+ * an error for protvirt, but protvirt means user cpu state
+ */
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
kvm_s390_vcpu_stop(vcpu);
return -EOPNOTSUPP;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 9ac73b717e25..036bff58e75a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2438,6 +2438,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
case KVM_S390_PV_COMMAND: {
struct kvm_pv_cmd args;
+ /* protvirt means user sigp */
+ kvm->arch.user_cpu_state_ctrl = 1;
r = 0;
if (!is_prot_virt_host()) {
r = -EINVAL;
@@ -3699,10 +3701,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
switch (mp_state->mp_state) {
case KVM_MP_STATE_STOPPED:
- kvm_s390_vcpu_stop(vcpu);
+ rc = kvm_s390_vcpu_stop(vcpu);
break;
case KVM_MP_STATE_OPERATING:
- kvm_s390_vcpu_start(vcpu);
+ rc = kvm_s390_vcpu_start(vcpu);
break;
case KVM_MP_STATE_LOAD:
case KVM_MP_STATE_CHECK_STOP:
@@ -4287,6 +4289,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_sigset_activate(vcpu);
+ /*
+ * no need to check the return value of vcpu_start as it can only have
+ * an error for protvirt, but protvirt means user cpu state
+ */
if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
kvm_s390_vcpu_start(vcpu);
} else if (is_vcpu_stopped(vcpu)) {
@@ -4424,12 +4430,12 @@ static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
}
-void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
+int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
- int i, online_vcpus, started_vcpus = 0;
+ int i, online_vcpus, r= 0, started_vcpus = 0;
if (!is_vcpu_stopped(vcpu))
- return;
+ return 0;
trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
/* Only one cpu at a time may enter/leave the STOPPED state. */
@@ -4452,7 +4458,9 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
*/
__disable_ibs_on_all_vcpus(vcpu->kvm);
}
-
+ /* Let's tell the UV that we want to start again */
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR);
kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED);
/*
* Another VCPU might have used IBS while we were offline.
@@ -4460,16 +4468,16 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
*/
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
spin_unlock(&vcpu->kvm->arch.start_stop_lock);
- return;
+ return r;
}
-void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
+int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
- int i, online_vcpus, started_vcpus = 0;
+ int i, online_vcpus, r = 0, started_vcpus = 0;
struct kvm_vcpu *started_vcpu = NULL;
if (is_vcpu_stopped(vcpu))
- return;
+ return 0;
trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
/* Only one cpu at a time may enter/leave the STOPPED state. */
@@ -4480,6 +4488,9 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
kvm_s390_clear_stop_irq(vcpu);
kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
+ /* Let's tell the UV that we successfully stopped the vcpu */
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_STP);
__disable_ibs_on_vcpu(vcpu);
for (i = 0; i < online_vcpus; i++) {
@@ -4498,7 +4509,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
}
spin_unlock(&vcpu->kvm->arch.start_stop_lock);
- return;
+ return r;
}
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index d62de29b2d6c..e9e1996d643b 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -219,6 +219,7 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc,
u16 *rrc);
int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
unsigned long tweak, u16 *rc, u16 *rrc);
+int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state);
static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm)
{
@@ -332,8 +333,8 @@ void kvm_s390_set_tod_clock(struct kvm *kvm,
long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
-void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
-void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
+int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
+int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu);
bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index a9c7e97d98e1..e9863382ee15 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -266,3 +266,21 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
KVM_UV_EVENT(kvm, 3, "%s", "PROTVIRT VM UNPACK: successful");
return ret;
}
+
+int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state)
+{
+ struct uv_cb_cpu_set_state uvcb = {
+ .header.cmd = UVC_CMD_CPU_SET_STATE,
+ .header.len = sizeof(uvcb),
+ .cpu_handle = kvm_s390_pv_cpu_get_handle(vcpu),
+ .state = state,
+ };
+ int cc;
+
+ cc = uv_call(0, (u64)&uvcb);
+ KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT SET CPU %d STATE %d rc %x rrc %x",
+ vcpu->vcpu_id, state, uvcb.header.rc, uvcb.header.rrc);
+ if (cc)
+ return -EINVAL;
+ return 0;
+}
--
2.25.0
^ permalink raw reply related
* [PATCH v3 16/37] KVM: s390: protvirt: Add SCLP interrupt handling
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Janosch Frank
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
The sclp interrupt is kind of special. The ultravisor polices that we
do not inject an sclp interrupt with payload if no sccb is outstanding.
On the other hand we have "asynchronous" event interrupts, e.g. for
console input.
We separate both variants into sclp interrupt and sclp event interrupt.
The sclp interrupt is masked until a previous servc instruction has
finished (sie exit 108).
[frankja@linux.ibm.com: factoring out write_sclp]
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/kvm_host.h | 6 +-
arch/s390/kvm/intercept.c | 27 +++++++++
arch/s390/kvm/interrupt.c | 95 ++++++++++++++++++++++++++------
arch/s390/kvm/kvm-s390.c | 4 ++
4 files changed, 113 insertions(+), 19 deletions(-)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index a13dc77f8b07..ba3364b37159 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -518,6 +518,7 @@ enum irq_types {
IRQ_PEND_PFAULT_INIT,
IRQ_PEND_EXT_HOST,
IRQ_PEND_EXT_SERVICE,
+ IRQ_PEND_EXT_SERVICE_EV,
IRQ_PEND_EXT_TIMING,
IRQ_PEND_EXT_CPU_TIMER,
IRQ_PEND_EXT_CLOCK_COMP,
@@ -562,6 +563,7 @@ enum irq_types {
(1UL << IRQ_PEND_EXT_TIMING) | \
(1UL << IRQ_PEND_EXT_HOST) | \
(1UL << IRQ_PEND_EXT_SERVICE) | \
+ (1UL << IRQ_PEND_EXT_SERVICE_EV) | \
(1UL << IRQ_PEND_VIRTIO) | \
(1UL << IRQ_PEND_PFAULT_INIT) | \
(1UL << IRQ_PEND_PFAULT_DONE))
@@ -582,7 +584,8 @@ enum irq_types {
(1UL << IRQ_PEND_EXT_CLOCK_COMP) | \
(1UL << IRQ_PEND_EXT_EMERGENCY) | \
(1UL << IRQ_PEND_EXT_EXTERNAL) | \
- (1UL << IRQ_PEND_EXT_SERVICE))
+ (1UL << IRQ_PEND_EXT_SERVICE) | \
+ (1UL << IRQ_PEND_EXT_SERVICE_EV))
struct kvm_s390_interrupt_info {
struct list_head list;
@@ -642,6 +645,7 @@ struct kvm_s390_local_interrupt {
struct kvm_s390_float_interrupt {
unsigned long pending_irqs;
+ unsigned long masked_irqs;
spinlock_t lock;
struct list_head lists[FIRQ_LIST_COUNT];
int counters[FIRQ_MAX_COUNT];
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 6fdbac696f65..d50a0214eba1 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -444,8 +444,35 @@ static int handle_operexc(struct kvm_vcpu *vcpu)
return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
}
+static int handle_pv_sclp(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+
+ spin_lock(&fi->lock);
+ /*
+ * 2 cases:
+ * a: an sccb answering interrupt was already pending or in flight.
+ * As the sccb value is not known we can simply set some value to
+ * trigger delivery of a saved SCCB. UV will then use its saved
+ * copy of the SCCB value.
+ * b: an error SCCB interrupt needs to be injected so we also inject
+ * a fake SCCB address. Firmware will use the proper one.
+ * This makes sure, that both errors and real sccb returns will only
+ * be delivered after a notification intercept (instruction has
+ * finished) but not after others.
+ */
+ fi->srv_signal.ext_params |= 0x43000;
+ set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
+ clear_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs);
+ spin_unlock(&fi->lock);
+ return 0;
+}
+
static int handle_pv_notification(struct kvm_vcpu *vcpu)
{
+ if (vcpu->arch.sie_block->ipa == 0xb220)
+ return handle_pv_sclp(vcpu);
+
return handle_instruction(vcpu);
}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 61310b1f5b62..aaff3dbd669e 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -324,8 +324,11 @@ static inline int gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu)
{
- return vcpu->kvm->arch.float_int.pending_irqs |
- vcpu->arch.local_int.pending_irqs;
+ unsigned long pending = vcpu->kvm->arch.float_int.pending_irqs |
+ vcpu->arch.local_int.pending_irqs;
+
+ pending &= ~vcpu->kvm->arch.float_int.masked_irqs;
+ return pending;
}
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
@@ -383,8 +386,10 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
__clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask);
if (!(vcpu->arch.sie_block->gcr[0] & CR0_CPU_TIMER_SUBMASK))
__clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask);
- if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK))
+ if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) {
__clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
+ __clear_bit(IRQ_PEND_EXT_SERVICE_EV, &active_mask);
+ }
if (psw_mchk_disabled(vcpu))
active_mask &= ~IRQ_PEND_MCHK_MASK;
/* PV guest cpus can have a single interruption injected at a time. */
@@ -946,20 +951,49 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
return rc ? -EFAULT : 0;
}
+#define SCCB_MASK 0xFFFFFFF8
+#define SCCB_EVENT_PENDING 0x3
+
+static int write_sclp(struct kvm_vcpu *vcpu, u32 parm)
+{
+ int rc;
+
+ if (kvm_s390_pv_cpu_get_handle(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_SERVICE_SIG;
+ vcpu->arch.sie_block->eiparams = parm;
+ return 0;
+ }
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= put_guest_lc(vcpu, parm,
+ (u32 *)__LC_EXT_PARAMS);
+
+ return rc ? -EFAULT : 0;
+}
+
static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_ext_info ext;
- int rc = 0;
spin_lock(&fi->lock);
- if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) {
+ if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs) ||
+ !(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) {
spin_unlock(&fi->lock);
return 0;
}
ext = fi->srv_signal;
memset(&fi->srv_signal, 0, sizeof(ext));
clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
+ clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs);
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ set_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs);
spin_unlock(&fi->lock);
VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x",
@@ -968,16 +1002,31 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
ext.ext_params, 0);
- rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= put_guest_lc(vcpu, ext.ext_params,
- (u32 *)__LC_EXT_PARAMS);
+ return write_sclp(vcpu, ext.ext_params);
+}
- return rc ? -EFAULT : 0;
+static int __must_check __deliver_service_ev(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct kvm_s390_ext_info ext;
+
+ spin_lock(&fi->lock);
+ if (!(test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs))) {
+ spin_unlock(&fi->lock);
+ return 0;
+ }
+ ext = fi->srv_signal;
+ /* only clear the event bit */
+ fi->srv_signal.ext_params &= ~SCCB_EVENT_PENDING;
+ clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+
+ VCPU_EVENT(vcpu, 4, "%s", "deliver: sclp parameter event");
+ vcpu->stat.deliver_service_signal++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
+ ext.ext_params, 0);
+
+ return write_sclp(vcpu, SCCB_EVENT_PENDING);
}
static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
@@ -1382,6 +1431,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
case IRQ_PEND_EXT_SERVICE:
rc = __deliver_service(vcpu);
break;
+ case IRQ_PEND_EXT_SERVICE_EV:
+ rc = __deliver_service_ev(vcpu);
+ break;
case IRQ_PEND_PFAULT_DONE:
rc = __deliver_pfault_done(vcpu);
break;
@@ -1734,9 +1786,6 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
return inti;
}
-#define SCCB_MASK 0xFFFFFFF8
-#define SCCB_EVENT_PENDING 0x3
-
static int __inject_service(struct kvm *kvm,
struct kvm_s390_interrupt_info *inti)
{
@@ -1745,6 +1794,11 @@ static int __inject_service(struct kvm *kvm,
kvm->stat.inject_service_signal++;
spin_lock(&fi->lock);
fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING;
+
+ /* We always allow events, track them separately from the sccb ints */
+ if (fi->srv_signal.ext_params & SCCB_EVENT_PENDING)
+ set_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs);
+
/*
* Early versions of the QEMU s390 bios will inject several
* service interrupts after another without handling a
@@ -2141,6 +2195,10 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
int i;
+ mutex_lock(&kvm->lock);
+ if (!kvm_s390_pv_is_protected(kvm))
+ fi->masked_irqs = 0;
+ mutex_unlock(&kvm->lock);
spin_lock(&fi->lock);
fi->pending_irqs = 0;
memset(&fi->srv_signal, 0, sizeof(fi->srv_signal));
@@ -2207,7 +2265,8 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
n++;
}
}
- if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) {
+ if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs) ||
+ test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs)) {
if (n == max_irqs) {
/* signal userspace to try again */
ret = -ENOMEM;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f99e4eb5c27b..f9e05b3f0289 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2236,6 +2236,8 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
if (r)
kvm_s390_pv_destroy_vm(kvm, &dummy, &dummy);
+ /* we need to block service interrupts from now on */
+ set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
break;
}
case KVM_PV_DISABLE: {
@@ -2247,6 +2249,8 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
r = kvm_s390_pv_destroy_vm(kvm, &cmd->rc, &cmd->rrc);
if (!r)
kvm_s390_pv_dealloc_vm(kvm);
+ /* no need to block service interrupts any more */
+ clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
break;
}
case KVM_PV_VM_SET_SEC_PARMS: {
--
2.25.0
^ permalink raw reply related
* [PATCH v3 05/37] s390/mm: provide memory management functions for protected KVM guests
From: Christian Borntraeger @ 2020-02-20 10:39 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, David Hildenbrand, Thomas Huth,
Ulrich Weigand, Claudio Imbrenda, linux-s390, Michael Mueller,
Vasily Gorbik, Andrea Arcangeli, linux-mm
In-Reply-To: <20200220104020.5343-1-borntraeger@de.ibm.com>
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
This provides the basic ultravisor calls and page table handling to cope
with secure guests:
- provide arch_make_page_accessible
- make pages accessible after unmapping of secure guests
- provide the ultravisor commands convert to/from secure
- provide the ultravisor commands pin/unpin shared
- provide callbacks to make pages secure (inacccessible)
- we check for the expected pin count to only make pages secure if the
host is not accessing them
- we fence hugetlbfs for secure pages
Co-developed-by: Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
Signed-off-by: Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
[borntraeger@de.ibm.com: patch merging, splitting, fixing]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/include/asm/gmap.h | 4 +
arch/s390/include/asm/mmu.h | 2 +
arch/s390/include/asm/mmu_context.h | 1 +
arch/s390/include/asm/page.h | 5 +
arch/s390/include/asm/pgtable.h | 35 ++++-
arch/s390/include/asm/uv.h | 31 ++++
arch/s390/kernel/uv.c | 227 ++++++++++++++++++++++++++++
7 files changed, 300 insertions(+), 5 deletions(-)
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 37f96b6f0e61..3c4926aa78f4 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -9,6 +9,7 @@
#ifndef _ASM_S390_GMAP_H
#define _ASM_S390_GMAP_H
+#include <linux/radix-tree.h>
#include <linux/refcount.h>
/* Generic bits for GMAP notification on DAT table entry changes. */
@@ -31,6 +32,7 @@
* @table: pointer to the page directory
* @asce: address space control element for gmap page table
* @pfault_enabled: defines if pfaults are applicable for the guest
+ * @guest_handle: protected virtual machine handle for the ultravisor
* @host_to_rmap: radix tree with gmap_rmap lists
* @children: list of shadow gmap structures
* @pt_list: list of all page tables used in the shadow guest address space
@@ -54,6 +56,8 @@ struct gmap {
unsigned long asce_end;
void *private;
bool pfault_enabled;
+ /* only set for protected virtual machines */
+ unsigned long guest_handle;
/* Additional data for shadow guest address spaces */
struct radix_tree_root host_to_rmap;
struct list_head children;
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index bcfb6371086f..e21b618ad432 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -16,6 +16,8 @@ typedef struct {
unsigned long asce;
unsigned long asce_limit;
unsigned long vdso_base;
+ /* The mmu context belongs to a secure guest. */
+ atomic_t is_protected;
/*
* The following bitfields need a down_write on the mm
* semaphore when they are written to. As they are only
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 8d04e6f3f796..afa836014076 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -23,6 +23,7 @@ static inline int init_new_context(struct task_struct *tsk,
INIT_LIST_HEAD(&mm->context.gmap_list);
cpumask_clear(&mm->context.cpu_attach_mask);
atomic_set(&mm->context.flush_count, 0);
+ atomic_set(&mm->context.is_protected, 0);
mm->context.gmap_asce = 0;
mm->context.flush_mm = 0;
mm->context.compat_mm = test_thread_flag(TIF_31BIT);
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 85e944f04c70..4ebcf891ff3c 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -153,6 +153,11 @@ static inline int devmem_is_allowed(unsigned long pfn)
#define HAVE_ARCH_FREE_PAGE
#define HAVE_ARCH_ALLOC_PAGE
+#if IS_ENABLED(CONFIG_PGSTE)
+int arch_make_page_accessible(struct page *page);
+#define HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
+#endif
+
#endif /* !__ASSEMBLY__ */
#define __PAGE_OFFSET 0x0UL
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 137a3920ca36..cc7a1adacb94 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -19,6 +19,7 @@
#include <linux/atomic.h>
#include <asm/bug.h>
#include <asm/page.h>
+#include <asm/uv.h>
extern pgd_t swapper_pg_dir[];
extern void paging_init(void);
@@ -520,6 +521,15 @@ static inline int mm_has_pgste(struct mm_struct *mm)
return 0;
}
+static inline int mm_is_protected(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+ if (unlikely(atomic_read(&mm->context.is_protected)))
+ return 1;
+#endif
+ return 0;
+}
+
static inline int mm_alloc_pgste(struct mm_struct *mm)
{
#ifdef CONFIG_PGSTE
@@ -1061,7 +1071,12 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
+ pte_t res;
+
+ res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
+ if (mm_is_protected(mm) && pte_present(res))
+ uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+ return res;
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -1073,7 +1088,12 @@ void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
- return ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID));
+ pte_t res;
+
+ res = ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID));
+ if (mm_is_protected(vma->vm_mm) && pte_present(res))
+ uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+ return res;
}
/*
@@ -1088,12 +1108,17 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep, int full)
{
+ pte_t res;
+
if (full) {
- pte_t pte = *ptep;
+ res = *ptep;
*ptep = __pte(_PAGE_INVALID);
- return pte;
+ } else {
+ res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
}
- return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
+ if (mm_is_protected(mm) && pte_present(res))
+ uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+ return res;
}
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index cad643b05d19..7956868340c1 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -15,6 +15,7 @@
#include <linux/errno.h>
#include <linux/bug.h>
#include <asm/page.h>
+#include <asm/gmap.h>
#define UVC_RC_EXECUTED 0x0001
#define UVC_RC_INV_CMD 0x0002
@@ -24,6 +25,10 @@
#define UVC_CMD_QUI 0x0001
#define UVC_CMD_INIT_UV 0x000f
+#define UVC_CMD_CONV_TO_SEC_STOR 0x0200
+#define UVC_CMD_CONV_FROM_SEC_STOR 0x0201
+#define UVC_CMD_PIN_PAGE_SHARED 0x0341
+#define UVC_CMD_UNPIN_PAGE_SHARED 0x0342
#define UVC_CMD_SET_SHARED_ACCESS 0x1000
#define UVC_CMD_REMOVE_SHARED_ACCESS 0x1001
@@ -31,8 +36,12 @@
enum uv_cmds_inst {
BIT_UVC_CMD_QUI = 0,
BIT_UVC_CMD_INIT_UV = 1,
+ BIT_UVC_CMD_CONV_TO_SEC_STOR = 6,
+ BIT_UVC_CMD_CONV_FROM_SEC_STOR = 7,
BIT_UVC_CMD_SET_SHARED_ACCESS = 8,
BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9,
+ BIT_UVC_CMD_PIN_PAGE_SHARED = 21,
+ BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22,
};
struct uv_cb_header {
@@ -69,6 +78,19 @@ struct uv_cb_init {
u64 reserved28[4];
} __packed __aligned(8);
+struct uv_cb_cts {
+ struct uv_cb_header header;
+ u64 reserved08[2];
+ u64 guest_handle;
+ u64 gaddr;
+} __packed __aligned(8);
+
+struct uv_cb_cfs {
+ struct uv_cb_header header;
+ u64 reserved08[2];
+ u64 paddr;
+} __packed __aligned(8);
+
struct uv_cb_share {
struct uv_cb_header header;
u64 reserved08[3];
@@ -171,12 +193,21 @@ static inline int is_prot_virt_host(void)
return prot_virt_host;
}
+int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
+int uv_convert_from_secure(unsigned long paddr);
+int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
+
void setup_uv(void);
void adjust_to_uv_max(unsigned long *vmax);
#else
#define is_prot_virt_host() 0
static inline void setup_uv(void) {}
static inline void adjust_to_uv_max(unsigned long *vmax) {}
+
+static inline int uv_convert_from_secure(unsigned long paddr)
+{
+ return 0;
+}
#endif
#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || \
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 1ddc42154ef6..4539003dac9d 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -12,6 +12,8 @@
#include <linux/sizes.h>
#include <linux/bitmap.h>
#include <linux/memblock.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
#include <asm/facility.h>
#include <asm/sections.h>
#include <asm/uv.h>
@@ -97,4 +99,229 @@ void adjust_to_uv_max(unsigned long *vmax)
{
*vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr);
}
+
+/*
+ * Requests the Ultravisor to pin the page in the shared state. This will
+ * cause an intercept when the guest attempts to unshare the pinned page.
+ */
+static int uv_pin_shared(unsigned long paddr)
+{
+ struct uv_cb_cfs uvcb = {
+ .header.cmd = UVC_CMD_PIN_PAGE_SHARED,
+ .header.len = sizeof(uvcb),
+ .paddr = paddr,
+ };
+
+ if (uv_call(0, (u64)&uvcb))
+ return -EINVAL;
+ return 0;
+}
+
+/*
+ * Requests the Ultravisor to encrypt a guest page and make it
+ * accessible to the host for paging (export).
+ *
+ * @paddr: Absolute host address of page to be exported
+ */
+int uv_convert_from_secure(unsigned long paddr)
+{
+ struct uv_cb_cfs uvcb = {
+ .header.cmd = UVC_CMD_CONV_FROM_SEC_STOR,
+ .header.len = sizeof(uvcb),
+ .paddr = paddr
+ };
+
+ if (uv_call(0, (u64)&uvcb))
+ return -EINVAL;
+ return 0;
+}
+
+/*
+ * Calculate the expected ref_count for a page that would otherwise have no
+ * further pins. This was cribbed from similar functions in other places in
+ * the kernel, but with some slight modifications. We know that a secure
+ * page can not be a huge page for example.
+ */
+static int expected_page_refs(struct page *page)
+{
+ int res;
+
+ res = page_mapcount(page);
+ if (PageSwapCache(page)) {
+ res++;
+ } else if (page_mapping(page)) {
+ res++;
+ if (page_has_private(page))
+ res++;
+ }
+ return res;
+}
+
+static int make_secure_pte(pte_t *ptep, unsigned long addr,
+ struct page *exp_page, struct uv_cb_header *uvcb)
+{
+ pte_t entry = READ_ONCE(*ptep);
+ struct page *page;
+ int expected, rc = 0;
+
+ if (!pte_present(entry))
+ return -ENXIO;
+ if (pte_val(entry) & _PAGE_INVALID)
+ return -ENXIO;
+
+ page = pte_page(entry);
+ if (page != exp_page)
+ return -ENXIO;
+ if (PageWriteback(page))
+ return -EAGAIN;
+ expected = expected_page_refs(page);
+ if (!page_ref_freeze(page, expected))
+ return -EBUSY;
+ set_bit(PG_arch_1, &page->flags);
+ rc = uv_call(0, (u64)uvcb);
+ page_ref_unfreeze(page, expected);
+ /* Return -ENXIO if the page was not mapped, -EINVAL otherwise */
+ if (rc)
+ rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
+ return rc;
+}
+
+/*
+ * Requests the Ultravisor to make a page accessible to a guest.
+ * If it's brought in the first time, it will be cleared. If
+ * it has been exported before, it will be decrypted and integrity
+ * checked.
+ */
+int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
+{
+ struct vm_area_struct *vma;
+ bool local_drain = false;
+ spinlock_t *ptelock;
+ unsigned long uaddr;
+ struct page *page;
+ pte_t *ptep;
+ int rc;
+
+again:
+ rc = -EFAULT;
+ down_read(&gmap->mm->mmap_sem);
+
+ uaddr = __gmap_translate(gmap, gaddr);
+ if (IS_ERR_VALUE(uaddr))
+ goto out;
+ vma = find_vma(gmap->mm, uaddr);
+ if (!vma)
+ goto out;
+ /*
+ * Secure pages cannot be huge and userspace should not combine both.
+ * In case userspace does it anyway this will result in an -EFAULT for
+ * the unpack. The guest is thus never reaching secure mode. If
+ * userspace is playing dirty tricky with mapping huge pages later
+ * on this will result in a segmentation fault.
+ */
+ if (is_vm_hugetlb_page(vma))
+ goto out;
+
+ rc = -ENXIO;
+ page = follow_page(vma, uaddr, FOLL_WRITE);
+ if (IS_ERR_OR_NULL(page))
+ goto out;
+
+ lock_page(page);
+ ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
+ rc = make_secure_pte(ptep, uaddr, page, uvcb);
+ pte_unmap_unlock(ptep, ptelock);
+ unlock_page(page);
+out:
+ up_read(&gmap->mm->mmap_sem);
+
+ if (rc == -EAGAIN) {
+ wait_on_page_writeback(page);
+ } else if (rc == -EBUSY) {
+ /*
+ * If we have tried a local drain and the page refcount
+ * still does not match our expected safe value, try with a
+ * system wide drain. This is needed if the pagevecs holding
+ * the page are on a different CPU.
+ */
+ if (local_drain) {
+ lru_add_drain_all();
+ /* We give up here, and let the caller try again */
+ return -EAGAIN;
+ }
+ /*
+ * We are here if the page refcount does not match the
+ * expected safe value. The main culprits are usually
+ * pagevecs. With lru_add_drain() we drain the pagevecs
+ * on the local CPU so that hopefully the refcount will
+ * reach the expected safe value.
+ */
+ lru_add_drain();
+ local_drain = true;
+ /* And now we try again immediately after draining */
+ goto again;
+ } else if (rc == -ENXIO) {
+ if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE))
+ return -EFAULT;
+ return -EAGAIN;
+ }
+ return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_make_secure);
+
+int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
+{
+ struct uv_cb_cts uvcb = {
+ .header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
+ .header.len = sizeof(uvcb),
+ .guest_handle = gmap->guest_handle,
+ .gaddr = gaddr,
+ };
+
+ return gmap_make_secure(gmap, gaddr, &uvcb);
+}
+EXPORT_SYMBOL_GPL(gmap_convert_to_secure);
+
+/*
+ * To be called with the page locked or with an extra reference! This will
+ * prevent gmap_make_secure from touching the page concurrently. Having 2
+ * parallel make_page_accessible is fine, as the UV calls will become a
+ * no-op if the page is already exported.
+ */
+int arch_make_page_accessible(struct page *page)
+{
+ int rc = 0;
+
+ /* Hugepage cannot be protected, so nothing to do */
+ if (PageHuge(page))
+ return 0;
+
+ /*
+ * PG_arch_1 is used in 3 places:
+ * 1. for kernel page tables during early boot
+ * 2. for storage keys of huge pages and KVM
+ * 3. As an indication that this page might be secure. This can
+ * overindicate, e.g. we set the bit before calling
+ * convert_to_secure.
+ * As secure pages are never huge, all 3 variants can co-exists.
+ */
+ if (!test_bit(PG_arch_1, &page->flags))
+ return 0;
+
+ rc = uv_pin_shared(page_to_phys(page));
+ if (!rc) {
+ clear_bit(PG_arch_1, &page->flags);
+ return 0;
+ }
+
+ rc = uv_convert_from_secure(page_to_phys(page));
+ if (!rc) {
+ clear_bit(PG_arch_1, &page->flags);
+ return 0;
+ }
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(arch_make_page_accessible);
+
#endif
--
2.25.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.