summaryrefslogtreecommitdiff
path: root/arch/s390/kvm/diag.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/kvm/diag.c')
-rw-r--r--arch/s390/kvm/diag.c250
1 files changed, 212 insertions, 38 deletions
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 3074475c8ae0..53233dec8cad 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* handling diagnose instructions
*
- * Copyright IBM Corp. 2008, 2011
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
+ * Copyright IBM Corp. 2008, 2020
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
@@ -13,67 +10,222 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <asm/gmap.h>
+#include <asm/gmap_helpers.h>
#include <asm/virtio-ccw.h>
#include "kvm-s390.h"
#include "trace.h"
#include "trace-s390.h"
+#include "gaccess.h"
+
+static void do_discard_gfn_range(struct kvm_vcpu *vcpu, gfn_t gfn_start, gfn_t gfn_end)
+{
+ struct kvm_memslot_iter iter;
+ struct kvm_memory_slot *slot;
+ struct kvm_memslots *slots;
+ unsigned long start, end;
+
+ slots = kvm_vcpu_memslots(vcpu);
+
+ kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
+ slot = iter.slot;
+ start = __gfn_to_hva_memslot(slot, max(gfn_start, slot->base_gfn));
+ end = __gfn_to_hva_memslot(slot, min(gfn_end, slot->base_gfn + slot->npages));
+ gmap_helper_discard(vcpu->kvm->mm, start, end);
+ }
+}
static int diag_release_pages(struct kvm_vcpu *vcpu)
{
unsigned long start, end;
- unsigned long prefix = vcpu->arch.sie_block->prefix;
+ unsigned long prefix = kvm_s390_get_prefix(vcpu);
start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
- end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
+ end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + PAGE_SIZE;
+ vcpu->stat.instruction_diagnose_10++;
- if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end
+ if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end
|| start < 2 * PAGE_SIZE)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end);
- vcpu->stat.diagnose_10++;
- /* we checked for start > end above */
- if (end < prefix || start >= prefix + 2 * PAGE_SIZE) {
- gmap_discard(start, end, vcpu->arch.gmap);
+ mmap_read_lock(vcpu->kvm->mm);
+ /*
+ * We checked for start >= end above, so lets check for the
+ * fast path (no prefix swap page involved)
+ */
+ if (end <= prefix || start >= prefix + 2 * PAGE_SIZE) {
+ do_discard_gfn_range(vcpu, gpa_to_gfn(start), gpa_to_gfn(end));
} else {
- if (start < prefix)
- gmap_discard(start, prefix, vcpu->arch.gmap);
- if (end >= prefix)
- gmap_discard(prefix + 2 * PAGE_SIZE,
- end, vcpu->arch.gmap);
+ /*
+ * This is slow path. gmap_discard will check for start
+ * so lets split this into before prefix, prefix, after
+ * prefix and let gmap_discard make some of these calls
+ * NOPs.
+ */
+ do_discard_gfn_range(vcpu, gpa_to_gfn(start), gpa_to_gfn(prefix));
+ if (start <= prefix)
+ do_discard_gfn_range(vcpu, 0, 1);
+ if (end > prefix + PAGE_SIZE)
+ do_discard_gfn_range(vcpu, 1, 2);
+ do_discard_gfn_range(vcpu, gpa_to_gfn(prefix) + 2, gpa_to_gfn(end));
}
+ mmap_read_unlock(vcpu->kvm->mm);
return 0;
}
+static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
+{
+ struct prs_parm {
+ u16 code;
+ u16 subcode;
+ u16 parm_len;
+ u16 parm_version;
+ u64 token_addr;
+ u64 select_mask;
+ u64 compare_mask;
+ u64 zarch;
+ };
+ struct prs_parm parm;
+ int rc;
+ u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4;
+ u16 ry = (vcpu->arch.sie_block->ipa & 0x0f);
+
+ VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx",
+ vcpu->run->s.regs.gprs[rx]);
+ vcpu->stat.instruction_diagnose_258++;
+ if (vcpu->run->s.regs.gprs[rx] & 7)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ rc = read_guest_real(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm));
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
+ if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ switch (parm.subcode) {
+ case 0: /* TOKEN */
+ VCPU_EVENT(vcpu, 3, "pageref token addr 0x%llx "
+ "select mask 0x%llx compare mask 0x%llx",
+ parm.token_addr, parm.select_mask, parm.compare_mask);
+ if (vcpu->arch.pfault_token != KVM_S390_PFAULT_TOKEN_INVALID) {
+ /*
+ * If the pagefault handshake is already activated,
+ * the token must not be changed. We have to return
+ * decimal 8 instead, as mandated in SC24-6084.
+ */
+ vcpu->run->s.regs.gprs[ry] = 8;
+ return 0;
+ }
+
+ if ((parm.compare_mask & parm.select_mask) != parm.compare_mask ||
+ parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ if (!kvm_is_gpa_in_memslot(vcpu->kvm, parm.token_addr))
+ return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+ vcpu->arch.pfault_token = parm.token_addr;
+ vcpu->arch.pfault_select = parm.select_mask;
+ vcpu->arch.pfault_compare = parm.compare_mask;
+ vcpu->run->s.regs.gprs[ry] = 0;
+ rc = 0;
+ break;
+ case 1: /*
+ * CANCEL
+ * Specification allows to let already pending tokens survive
+ * the cancel, therefore to reduce code complexity, we assume
+ * all outstanding tokens are already pending.
+ */
+ VCPU_EVENT(vcpu, 3, "pageref cancel addr 0x%llx", parm.token_addr);
+ if (parm.token_addr || parm.select_mask ||
+ parm.compare_mask || parm.zarch)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ vcpu->run->s.regs.gprs[ry] = 0;
+ /*
+ * If the pfault handling was not established or is already
+ * canceled SC24-6084 requests to return decimal 4.
+ */
+ if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
+ vcpu->run->s.regs.gprs[ry] = 4;
+ else
+ vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+
+ rc = 0;
+ break;
+ default:
+ rc = -EOPNOTSUPP;
+ break;
+ }
+
+ return rc;
+}
+
static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
- vcpu->stat.diagnose_44++;
- kvm_vcpu_on_spin(vcpu);
+ vcpu->stat.instruction_diagnose_44++;
+ kvm_vcpu_on_spin(vcpu, true);
return 0;
}
+static int forward_cnt;
+static unsigned long cur_slice;
+
+static int diag9c_forwarding_overrun(void)
+{
+ /* Reset the count on a new slice */
+ if (time_after(jiffies, cur_slice)) {
+ cur_slice = jiffies;
+ forward_cnt = diag9c_forwarding_hz / HZ;
+ }
+ return forward_cnt-- <= 0 ? 1 : 0;
+}
+
static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
{
- struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tcpu;
+ int tcpu_cpu;
int tid;
- int i;
tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
- vcpu->stat.diagnose_9c++;
- VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid);
+ vcpu->stat.instruction_diagnose_9c++;
+ /* yield to self */
if (tid == vcpu->vcpu_id)
+ goto no_yield;
+
+ /* yield to invalid */
+ tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
+ if (!tcpu)
+ goto no_yield;
+
+ /* target guest VCPU already running */
+ tcpu_cpu = READ_ONCE(tcpu->cpu);
+ if (tcpu_cpu >= 0) {
+ if (!diag9c_forwarding_hz || diag9c_forwarding_overrun())
+ goto no_yield;
+
+ /* target host CPU already running */
+ if (!vcpu_is_preempted(tcpu_cpu))
+ goto no_yield;
+ smp_yield_cpu(tcpu_cpu);
+ VCPU_EVENT(vcpu, 5,
+ "diag time slice end directed to %d: yield forwarded",
+ tid);
+ vcpu->stat.diag_9c_forward++;
return 0;
+ }
- kvm_for_each_vcpu(i, tcpu, kvm)
- if (tcpu->vcpu_id == tid) {
- kvm_vcpu_yield_to(tcpu);
- break;
- }
+ if (kvm_vcpu_yield_to(tcpu) <= 0)
+ goto no_yield;
+ VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: done", tid);
+ return 0;
+no_yield:
+ VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid);
+ vcpu->stat.diag_9c_ignored++;
return 0;
}
@@ -82,7 +234,8 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
- VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
+ VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode);
+ vcpu->stat.instruction_diagnose_308++;
switch (subcode) {
case 3:
vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
@@ -94,7 +247,12 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
}
- atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+ /*
+ * 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;
vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
@@ -107,30 +265,43 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
{
- int ret, idx;
+ int ret;
+ vcpu->stat.instruction_diagnose_500++;
/* No virtio-ccw notification? Get out quickly. */
if (!vcpu->kvm->arch.css_support ||
(vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))
return -EOPNOTSUPP;
- idx = srcu_read_lock(&vcpu->kvm->srcu);
+ VCPU_EVENT(vcpu, 4, "diag 0x500 schid 0x%8.8x queue 0x%x cookie 0x%llx",
+ (u32) vcpu->run->s.regs.gprs[2],
+ (u32) vcpu->run->s.regs.gprs[3],
+ vcpu->run->s.regs.gprs[4]);
+
/*
* The layout is as follows:
* - gpr 2 contains the subchannel id (passed as addr)
* - gpr 3 contains the virtqueue index (passed as datamatch)
+ * - gpr 4 contains the index on the bus (optionally)
+ */
+ ret = kvm_io_bus_write_cookie(vcpu, KVM_VIRTIO_CCW_NOTIFY_BUS,
+ vcpu->run->s.regs.gprs[2] & 0xffffffff,
+ 8, &vcpu->run->s.regs.gprs[3],
+ vcpu->run->s.regs.gprs[4]);
+
+ /*
+ * Return cookie in gpr 2, but don't overwrite the register if the
+ * diagnose will be handled by userspace.
*/
- ret = kvm_io_bus_write(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS,
- vcpu->run->s.regs.gprs[2],
- 8, &vcpu->run->s.regs.gprs[3]);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
- /* kvm_io_bus_write returns -EOPNOTSUPP if it found no match. */
+ if (ret != -EOPNOTSUPP)
+ vcpu->run->s.regs.gprs[2] = ret;
+ /* kvm_io_bus_write_cookie returns -EOPNOTSUPP if it found no match. */
return ret < 0 ? ret : 0;
}
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
{
- int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
+ int code = kvm_s390_get_base_disp_rs(vcpu, NULL) & 0xffff;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -143,11 +314,14 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
return __diag_time_slice_end(vcpu);
case 0x9c:
return __diag_time_slice_end_directed(vcpu);
+ case 0x258:
+ return __diag_page_ref_service(vcpu);
case 0x308:
return __diag_ipl_functions(vcpu);
case 0x500:
return __diag_virtio_hypercall(vcpu);
default:
+ vcpu->stat.instruction_diagnose_other++;
return -EOPNOTSUPP;
}
}
generated by cgit (git 2.34.1) at 2025-12-25 05:54:24 +0000