qemu/hw/ppc/spapr_cpu_core.c

401 lines
11 KiB
C
Raw Normal View History

/*
* sPAPR CPU core device, acts as container of CPU thread devices.
*
* Copyright (C) 2016 Bharata B Rao <bharata@linux.vnet.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "hw/cpu/core.h"
#include "hw/ppc/spapr_cpu_core.h"
#include "hw/qdev-properties.h"
#include "migration/vmstate.h"
#include "target/ppc/cpu.h"
#include "hw/ppc/spapr.h"
#include "qapi/error.h"
#include "sysemu/cpus.h"
#include "sysemu/kvm.h"
#include "target/ppc/kvm_ppc.h"
#include "hw/ppc/ppc.h"
#include "target/ppc/mmu-hash64.h"
#include "target/ppc/power8-pmu.h"
#include "sysemu/numa.h"
#include "sysemu/reset.h"
#include "sysemu/hw_accel.h"
#include "qemu/error-report.h"
static void spapr_reset_vcpu(PowerPCCPU *cpu)
{
CPUState *cs = CPU(cpu);
CPUPPCState *env = &cpu->env;
PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
target_ulong lpcr;
SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
cpu_reset(cs);
/*
* "PowerPC Processor binding to IEEE 1275" defines the initial MSR state
* as 32bit (MSR_SF=0) in "8.2.1. Initial Register Values".
*/
env->msr &= ~(1ULL << MSR_SF);
env->spr[SPR_HIOR] = 0;
lpcr = env->spr[SPR_LPCR];
/* Set emulated LPCR to not send interrupts to hypervisor. Note that
* under KVM, the actual HW LPCR will be set differently by KVM itself,
* the settings below ensure proper operations with TCG in absence of
* a real hypervisor.
*
* Disable Power-saving mode Exit Cause exceptions for the CPU, so
* we don't get spurious wakups before an RTAS start-cpu call.
target/ppc: Set PSSCR_EC on cpu halt to prevent spurious wakeup The processor stop status and control register (PSSCR) is used to control the power saving facilities of the thread. The exit criterion bit (EC) is used to specify whether the thread should be woken by any interrupt (EC == 0) or only an interrupt enabled in the LPCR to wake the thread (EC == 1). The rtas facilities start-cpu and self-stop are used to transition a vcpu between the stopped and running states. When a vcpu is stopped it may only be started again by the start-cpu rtas call. Currently a vcpu in the stopped state will start again whenever an interrupt comes along due to PSSCR_EC being cleared, and while this is architecturally correct for a hardware thread, a vcpu is expected to only be woken by calling start-cpu. This means when performing a reboot on a tcg machine that the secondary threads will restart while the primary is still in slof, this is unsupported and causes call traces like: SLOF ********************************************************************** QEMU Starting Build Date = Jan 14 2019 18:00:39 FW Version = git-a5b428e1c1eae703 Press "s" to enter Open Firmware. qemu: fatal: Trying to deliver HV exception (MSR) 70 with no HV support NIP 6d61676963313230 LR 000000003dbe0308 CTR 6d61676963313233 XER 0000000000000000 CPU#1 MSR 0000000000000000 HID0 0000000000000000 HF 0000000000000000 iidx 3 didx 3 TB 00000026 115746031956 DECR 18446744073326238463 GPR00 000000003dbe0308 000000003e669fe0 000000003dc10700 0000000000000003 GPR04 000000003dc62198 000000003dc62178 000000003dc0ea48 0000000000000030 GPR08 000000003dc621a8 0000000000000018 000000003e466008 000000003dc50700 GPR12 c00000000093a4e0 c00000003ffff300 c00000003e533f90 0000000000000000 GPR16 0000000000000000 0000000000000000 000000003e466010 000000003dc0b040 GPR20 0000000000008000 000000000000f003 0000000000000006 000000003e66a050 GPR24 000000003dc06400 000000003dc0ae70 0000000000000003 000000000000f001 GPR28 000000003e66a060 ffffffffffffffff 6d61676963313233 0000000000000028 CR 28000222 [ E L - - - E E E ] RES ffffffffffffffff FPR00 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR04 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR08 0000000000000000 0000000000000000 0000000000000000 00000000311825e0 FPR12 00000000311825e0 0000000000000000 0000000000000000 0000000000000000 FPR16 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR20 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR24 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR28 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPSCR 0000000000000000 SRR0 000000003dbe06b0 SRR1 0000000000080000 PVR 00000000004e1200 VRSAVE 0000000000000000 SPRG0 000000003dbe0308 SPRG1 000000003e669fe0 SPRG2 00000000000000d8 SPRG3 000000003dbe0308 SPRG4 0000000000000000 SPRG5 0000000000000000 SPRG6 0000000000000000 SPRG7 0000000000000000 HSRR0 6d61676963313230 HSRR1 0000000000000000 CFAR 000000003dbe3e64 LPCR 0000000004020008 PTCR 0000000000000000 DAR 0000000000000000 DSISR 0000000000000000 Aborted (core dumped) To fix this, set the PSSCR_EC bit when a vcpu is stopped to disable it from coming back online until the start-cpu rtas call is made. Fixes: 21c0d66a9c99 ("target/ppc: Fix support for "STOP light" states on POWER9") Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Message-Id: <20190516005744.24366-1-sjitindarsingh@gmail.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-05-16 03:57:44 +03:00
* For the same reason, set PSSCR_EC.
*/
lpcr &= ~(LPCR_VPM1 | LPCR_ISL | LPCR_KBV | pcc->lpcr_pm);
lpcr |= LPCR_LPES0 | LPCR_LPES1;
target/ppc: Set PSSCR_EC on cpu halt to prevent spurious wakeup The processor stop status and control register (PSSCR) is used to control the power saving facilities of the thread. The exit criterion bit (EC) is used to specify whether the thread should be woken by any interrupt (EC == 0) or only an interrupt enabled in the LPCR to wake the thread (EC == 1). The rtas facilities start-cpu and self-stop are used to transition a vcpu between the stopped and running states. When a vcpu is stopped it may only be started again by the start-cpu rtas call. Currently a vcpu in the stopped state will start again whenever an interrupt comes along due to PSSCR_EC being cleared, and while this is architecturally correct for a hardware thread, a vcpu is expected to only be woken by calling start-cpu. This means when performing a reboot on a tcg machine that the secondary threads will restart while the primary is still in slof, this is unsupported and causes call traces like: SLOF ********************************************************************** QEMU Starting Build Date = Jan 14 2019 18:00:39 FW Version = git-a5b428e1c1eae703 Press "s" to enter Open Firmware. qemu: fatal: Trying to deliver HV exception (MSR) 70 with no HV support NIP 6d61676963313230 LR 000000003dbe0308 CTR 6d61676963313233 XER 0000000000000000 CPU#1 MSR 0000000000000000 HID0 0000000000000000 HF 0000000000000000 iidx 3 didx 3 TB 00000026 115746031956 DECR 18446744073326238463 GPR00 000000003dbe0308 000000003e669fe0 000000003dc10700 0000000000000003 GPR04 000000003dc62198 000000003dc62178 000000003dc0ea48 0000000000000030 GPR08 000000003dc621a8 0000000000000018 000000003e466008 000000003dc50700 GPR12 c00000000093a4e0 c00000003ffff300 c00000003e533f90 0000000000000000 GPR16 0000000000000000 0000000000000000 000000003e466010 000000003dc0b040 GPR20 0000000000008000 000000000000f003 0000000000000006 000000003e66a050 GPR24 000000003dc06400 000000003dc0ae70 0000000000000003 000000000000f001 GPR28 000000003e66a060 ffffffffffffffff 6d61676963313233 0000000000000028 CR 28000222 [ E L - - - E E E ] RES ffffffffffffffff FPR00 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR04 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR08 0000000000000000 0000000000000000 0000000000000000 00000000311825e0 FPR12 00000000311825e0 0000000000000000 0000000000000000 0000000000000000 FPR16 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR20 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR24 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPR28 0000000000000000 0000000000000000 0000000000000000 0000000000000000 FPSCR 0000000000000000 SRR0 000000003dbe06b0 SRR1 0000000000080000 PVR 00000000004e1200 VRSAVE 0000000000000000 SPRG0 000000003dbe0308 SPRG1 000000003e669fe0 SPRG2 00000000000000d8 SPRG3 000000003dbe0308 SPRG4 0000000000000000 SPRG5 0000000000000000 SPRG6 0000000000000000 SPRG7 0000000000000000 HSRR0 6d61676963313230 HSRR1 0000000000000000 CFAR 000000003dbe3e64 LPCR 0000000004020008 PTCR 0000000000000000 DAR 0000000000000000 DSISR 0000000000000000 Aborted (core dumped) To fix this, set the PSSCR_EC bit when a vcpu is stopped to disable it from coming back online until the start-cpu rtas call is made. Fixes: 21c0d66a9c99 ("target/ppc: Fix support for "STOP light" states on POWER9") Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com> Message-Id: <20190516005744.24366-1-sjitindarsingh@gmail.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-05-16 03:57:44 +03:00
env->spr[SPR_PSSCR] |= PSSCR_EC;
ppc_store_lpcr(cpu, lpcr);
/* Set a full AMOR so guest can use the AMR as it sees fit */
env->spr[SPR_AMOR] = 0xffffffffffffffffull;
spapr_cpu->vpa_addr = 0;
spapr_cpu->slb_shadow_addr = 0;
spapr_cpu->slb_shadow_size = 0;
spapr_cpu->dtl_addr = 0;
spapr_cpu->dtl_size = 0;
spapr_caps_cpu_apply(spapr, cpu);
2018-04-16 09:19:52 +03:00
kvm_check_mmu(cpu, &error_fatal);
spapr_irq_cpu_intc_reset(spapr, cpu);
}
void spapr_cpu_set_entry_state(PowerPCCPU *cpu, target_ulong nip,
target_ulong r1, target_ulong r3,
target_ulong r4)
{
PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
CPUPPCState *env = &cpu->env;
env->nip = nip;
env->gpr[1] = r1;
env->gpr[3] = r3;
env->gpr[4] = r4;
kvmppc_set_reg_ppc_online(cpu, 1);
CPU(cpu)->halted = 0;
/* Enable Power-saving mode Exit Cause exceptions */
ppc_store_lpcr(cpu, env->spr[SPR_LPCR] | pcc->lpcr_pm);
}
/*
* Return the sPAPR CPU core type for @model which essentially is the CPU
* model specified with -cpu cmdline option.
*/
const char *spapr_get_cpu_core_type(const char *cpu_type)
{
int len = strlen(cpu_type) - strlen(POWERPC_CPU_TYPE_SUFFIX);
char *core_type = g_strdup_printf(SPAPR_CPU_CORE_TYPE_NAME("%.*s"),
len, cpu_type);
ObjectClass *oc = object_class_by_name(core_type);
g_free(core_type);
if (!oc) {
return NULL;
}
return object_class_get_name(oc);
}
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
static bool slb_shadow_needed(void *opaque)
{
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuState *spapr_cpu = opaque;
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
return spapr_cpu->slb_shadow_addr != 0;
}
static const VMStateDescription vmstate_spapr_cpu_slb_shadow = {
.name = "spapr_cpu/vpa/slb_shadow",
.version_id = 1,
.minimum_version_id = 1,
.needed = slb_shadow_needed,
.fields = (VMStateField[]) {
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
VMSTATE_UINT64(slb_shadow_addr, SpaprCpuState),
VMSTATE_UINT64(slb_shadow_size, SpaprCpuState),
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
VMSTATE_END_OF_LIST()
}
};
static bool dtl_needed(void *opaque)
{
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuState *spapr_cpu = opaque;
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
return spapr_cpu->dtl_addr != 0;
}
static const VMStateDescription vmstate_spapr_cpu_dtl = {
.name = "spapr_cpu/vpa/dtl",
.version_id = 1,
.minimum_version_id = 1,
.needed = dtl_needed,
.fields = (VMStateField[]) {
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
VMSTATE_UINT64(dtl_addr, SpaprCpuState),
VMSTATE_UINT64(dtl_size, SpaprCpuState),
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
VMSTATE_END_OF_LIST()
}
};
static bool vpa_needed(void *opaque)
{
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuState *spapr_cpu = opaque;
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
return spapr_cpu->vpa_addr != 0;
}
static const VMStateDescription vmstate_spapr_cpu_vpa = {
.name = "spapr_cpu/vpa",
.version_id = 1,
.minimum_version_id = 1,
.needed = vpa_needed,
.fields = (VMStateField[]) {
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
VMSTATE_UINT64(vpa_addr, SpaprCpuState),
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
VMSTATE_END_OF_LIST()
},
.subsections = (const VMStateDescription * []) {
&vmstate_spapr_cpu_slb_shadow,
&vmstate_spapr_cpu_dtl,
NULL
}
};
static const VMStateDescription vmstate_spapr_cpu_state = {
.name = "spapr_cpu",
.version_id = 1,
.minimum_version_id = 1,
.fields = (VMStateField[]) {
VMSTATE_END_OF_LIST()
},
spapr_cpu_core: migrate VPA related state QEMU implements the "Shared Processor LPAR" (SPLPAR) option, which allows the hypervisor to time-slice a physical processor into multiple virtual processor. The intent is to allow more guests to run, and to optimize processor utilization. The guest OS can cede idle VCPUs, so that their processing capacity may be used by other VCPUs, with the H_CEDE hcall. The guest OS can also optimize spinlocks, by confering the time-slice of a spinning VCPU to the spinlock holder if it's currently notrunning, with the H_CONFER hcall. Both hcalls depend on a "Virtual Processor Area" (VPA) to be registered by the guest OS, generally during early boot. Other per-VCPU areas can be registered: the "SLB Shadow Buffer" which allows a more efficient dispatching of VCPUs, and the "Dispatch Trace Log Buffer" (DTL) which is used to compute time stolen by the hypervisor. Both DTL and SLB Shadow areas depend on the VPA to be registered. The VPA/SLB Shadow/DTL are state that QEMU should migrate, but this doesn't happen, for no apparent reason other than it was just never coded. This causes the features listed above to stop working after migration, and it breaks the logic of the H_REGISTER_VPA hcall in the destination. The VPA is set at the guest request, ie, we don't have to migrate it before the guest has actually set it. This patch hence adds an "spapr_cpu/vpa" subsection to the recently introduced per-CPU machine data migration stream. Since DTL and SLB Shadow are optional and both depend on VPA, they get their own subsections "spapr_cpu/vpa/slb_shadow" and "spapr_cpu/vpa/dtl" hanging from the "spapr_cpu/vpa" subsection. Note that this won't break migration to older QEMUs. Is is already handled by only registering the vmstate handler for per-CPU data with newer machine types. Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2018-06-18 15:26:49 +03:00
.subsections = (const VMStateDescription * []) {
&vmstate_spapr_cpu_vpa,
NULL
}
};
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
static void spapr_unrealize_vcpu(PowerPCCPU *cpu, SpaprCpuCore *sc)
{
hw/ppc: free env->tb_env in spapr_unrealize_vcpu() The timebase is allocated during spapr_realize_vcpu() and it's not freed. This results in memory leaks when doing vcpu unplugs: ==636935== ==636935== 144 (96 direct, 48 indirect) bytes in 1 blocks are definitely lost in loss record 6 ,461 of 8,135 ==636935== at 0x4897468: calloc (vg_replace_malloc.c:760) ==636935== by 0x5077213: g_malloc0 (in /usr/lib64/libglib-2.0.so.0.6400.4) ==636935== by 0x507757F: g_malloc0_n (in /usr/lib64/libglib-2.0.so.0.6400.4) ==636935== by 0x93C3FB: cpu_ppc_tb_init (ppc.c:1066) ==636935== by 0x97BC2B: spapr_realize_vcpu (spapr_cpu_core.c:268) ==636935== by 0x97C01F: spapr_cpu_core_realize (spapr_cpu_core.c:337) ==636935== by 0xD4626F: device_set_realized (qdev.c:531) ==636935== by 0xD55273: property_set_bool (object.c:2273) ==636935== by 0xD523DF: object_property_set (object.c:1408) ==636935== by 0xD588B7: object_property_set_qobject (qom-qobject.c:28) ==636935== by 0xD52897: object_property_set_bool (object.c:1477) ==636935== by 0xD4579B: qdev_realize (qdev.c:333) ==636935== This patch adds a cpu_ppc_tb_free() helper in hw/ppc/ppc.c to allow us to free the timebase. This leak is then solved by calling cpu_ppc_tb_free() in spapr_unrealize_vcpu(). Fixes: 6f4b5c3ec590 ("spapr: CPU hot unplug support") Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Message-Id: <20220329124545.529145-2-danielhb413@gmail.com> Signed-off-by: Cédric Le Goater <clg@kaod.org>
2022-04-04 09:49:06 +03:00
CPUPPCState *env = &cpu->env;
if (!sc->pre_3_0_migration) {
vmstate_unregister(NULL, &vmstate_spapr_cpu_state, cpu->machine_data);
}
spapr_irq_cpu_intc_destroy(SPAPR_MACHINE(qdev_get_machine()), cpu);
hw/ppc: free env->tb_env in spapr_unrealize_vcpu() The timebase is allocated during spapr_realize_vcpu() and it's not freed. This results in memory leaks when doing vcpu unplugs: ==636935== ==636935== 144 (96 direct, 48 indirect) bytes in 1 blocks are definitely lost in loss record 6 ,461 of 8,135 ==636935== at 0x4897468: calloc (vg_replace_malloc.c:760) ==636935== by 0x5077213: g_malloc0 (in /usr/lib64/libglib-2.0.so.0.6400.4) ==636935== by 0x507757F: g_malloc0_n (in /usr/lib64/libglib-2.0.so.0.6400.4) ==636935== by 0x93C3FB: cpu_ppc_tb_init (ppc.c:1066) ==636935== by 0x97BC2B: spapr_realize_vcpu (spapr_cpu_core.c:268) ==636935== by 0x97C01F: spapr_cpu_core_realize (spapr_cpu_core.c:337) ==636935== by 0xD4626F: device_set_realized (qdev.c:531) ==636935== by 0xD55273: property_set_bool (object.c:2273) ==636935== by 0xD523DF: object_property_set (object.c:1408) ==636935== by 0xD588B7: object_property_set_qobject (qom-qobject.c:28) ==636935== by 0xD52897: object_property_set_bool (object.c:1477) ==636935== by 0xD4579B: qdev_realize (qdev.c:333) ==636935== This patch adds a cpu_ppc_tb_free() helper in hw/ppc/ppc.c to allow us to free the timebase. This leak is then solved by calling cpu_ppc_tb_free() in spapr_unrealize_vcpu(). Fixes: 6f4b5c3ec590 ("spapr: CPU hot unplug support") Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Message-Id: <20220329124545.529145-2-danielhb413@gmail.com> Signed-off-by: Cédric Le Goater <clg@kaod.org>
2022-04-04 09:49:06 +03:00
cpu_ppc_tb_free(env);
qdev_unrealize(DEVICE(cpu));
}
/*
* Called when CPUs are hot-plugged.
*/
static void spapr_cpu_core_reset(DeviceState *dev)
{
CPUCore *cc = CPU_CORE(dev);
SpaprCpuCore *sc = SPAPR_CPU_CORE(dev);
int i;
for (i = 0; i < cc->nr_threads; i++) {
spapr_reset_vcpu(sc->threads[i]);
}
}
/*
* Called by the machine reset.
*/
static void spapr_cpu_core_reset_handler(void *opaque)
{
spapr_cpu_core_reset(opaque);
}
static void spapr_delete_vcpu(PowerPCCPU *cpu)
{
SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
cpu->machine_data = NULL;
g_free(spapr_cpu);
object_unparent(OBJECT(cpu));
}
qdev: Unrealize must not fail Devices may have component devices and buses. Device realization may fail. Realization is recursive: a device's realize() method realizes its components, and device_set_realized() realizes its buses (which should in turn realize the devices on that bus, except bus_set_realized() doesn't implement that, yet). When realization of a component or bus fails, we need to roll back: unrealize everything we realized so far. If any of these unrealizes failed, the device would be left in an inconsistent state. Must not happen. device_set_realized() lets it happen: it ignores errors in the roll back code starting at label child_realize_fail. Since realization is recursive, unrealization must be recursive, too. But how could a partly failed unrealize be rolled back? We'd have to re-realize, which can fail. This design is fundamentally broken. device_set_realized() does not roll back at all. Instead, it keeps unrealizing, ignoring further errors. It can screw up even for a device with no buses: if the lone dc->unrealize() fails, it still unregisters vmstate, and calls listeners' unrealize() callback. bus_set_realized() does not roll back either. Instead, it stops unrealizing. Fortunately, no unrealize method can fail, as we'll see below. To fix the design error, drop parameter @errp from all the unrealize methods. Any unrealize method that uses @errp now needs an update. This leads us to unrealize() methods that can fail. Merely passing it to another unrealize method cannot cause failure, though. Here are the ones that do other things with @errp: * virtio_serial_device_unrealize() Fails when qbus_set_hotplug_handler() fails, but still does all the other work. On failure, the device would stay realized with its resources completely gone. Oops. Can't happen, because qbus_set_hotplug_handler() can't actually fail here. Pass &error_abort to qbus_set_hotplug_handler() instead. * hw/ppc/spapr_drc.c's unrealize() Fails when object_property_del() fails, but all the other work is already done. On failure, the device would stay realized with its vmstate registration gone. Oops. Can't happen, because object_property_del() can't actually fail here. Pass &error_abort to object_property_del() instead. * spapr_phb_unrealize() Fails and bails out when remove_drcs() fails, but other work is already done. On failure, the device would stay realized with some of its resources gone. Oops. remove_drcs() fails only when chassis_from_bus()'s object_property_get_uint() fails, and it can't here. Pass &error_abort to remove_drcs() instead. Therefore, no unrealize method can fail before this patch. device_set_realized()'s recursive unrealization via bus uses object_property_set_bool(). Can't drop @errp there, so pass &error_abort. We similarly unrealize with object_property_set_bool() elsewhere, always ignoring errors. Pass &error_abort instead. Several unrealize methods no longer handle errors from other unrealize methods: virtio_9p_device_unrealize(), virtio_input_device_unrealize(), scsi_qdev_unrealize(), ... Much of the deleted error handling looks wrong anyway. One unrealize methods no longer ignore such errors: usb_ehci_pci_exit(). Several realize methods no longer ignore errors when rolling back: v9fs_device_realize_common(), pci_qdev_unrealize(), spapr_phb_realize(), usb_qdev_realize(), vfio_ccw_realize(), virtio_device_realize(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200505152926.18877-17-armbru@redhat.com>
2020-05-05 18:29:24 +03:00
static void spapr_cpu_core_unrealize(DeviceState *dev)
{
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuCore *sc = SPAPR_CPU_CORE(OBJECT(dev));
CPUCore *cc = CPU_CORE(dev);
int i;
for (i = 0; i < cc->nr_threads; i++) {
if (sc->threads[i]) {
/*
* Since this we can get here from the error path of
* spapr_cpu_core_realize(), make sure we only unrealize
* vCPUs that have already been realized.
*/
if (object_property_get_bool(OBJECT(sc->threads[i]), "realized",
&error_abort)) {
spapr_unrealize_vcpu(sc->threads[i], sc);
}
spapr_delete_vcpu(sc->threads[i]);
}
}
g_free(sc->threads);
qemu_unregister_reset(spapr_cpu_core_reset_handler, sc);
}
static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuCore *sc, Error **errp)
{
CPUPPCState *env = &cpu->env;
CPUState *cs = CPU(cpu);
if (!qdev_realize(DEVICE(cpu), NULL, errp)) {
return false;
}
cpu_ppc_set_vhyp(cpu, PPC_VIRTUAL_HYPERVISOR(spapr));
kvmppc_set_papr(cpu);
/* Set time-base frequency to 512 MHz. vhyp must be set first. */
cpu_ppc_tb_init(env, SPAPR_TIMEBASE_FREQ);
if (spapr_irq_cpu_intc_create(spapr, cpu, errp) < 0) {
qdev_unrealize(DEVICE(cpu));
return false;
}
if (!sc->pre_3_0_migration) {
vmstate_register(NULL, cs->cpu_index, &vmstate_spapr_cpu_state,
cpu->machine_data);
}
return true;
}
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
static PowerPCCPU *spapr_create_vcpu(SpaprCpuCore *sc, int i, Error **errp)
{
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuCoreClass *scc = SPAPR_CPU_CORE_GET_CLASS(sc);
CPUCore *cc = CPU_CORE(sc);
g_autoptr(Object) obj = NULL;
g_autofree char *id = NULL;
CPUState *cs;
PowerPCCPU *cpu;
obj = object_new(scc->cpu_type);
cs = CPU(obj);
cpu = POWERPC_CPU(obj);
ppc/spapr: Use start-powered-off CPUState property PowerPC sPAPR CPUs start in the halted state, and spapr_reset_vcpu() attempts to implement this by setting CPUState::halted to 1. But that's too late for the case of hotplugged CPUs in a machine configure with 2 or more threads per core. By then, other parts of QEMU have already caused the vCPU to run in an unitialized state a couple of times. For example, ppc_cpu_reset() calls ppc_tlb_invalidate_all(), which ends up calling async_run_on_cpu(). This kicks the new vCPU while it has CPUState::halted = 0, causing QEMU to issue a KVM_RUN ioctl on the new vCPU before the guest is able to make the start-cpu RTAS call to initialize its register state. This problem doesn't seem to cause visible issues for regular guests, but on a secure guest running under the Ultravisor it does. The Ultravisor relies on being able to snoop on the start-cpu RTAS call to map vCPUs to guests, and this issue causes it to see a stray vCPU that doesn't belong to any guest. Fix by setting the start-powered-off CPUState property in spapr_create_vcpu(), which makes cpu_common_reset() initialize CPUState::halted to 1 at an earlier moment. Suggested-by: Eduardo Habkost <ehabkost@redhat.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Greg Kurz <groug@kaod.org> Signed-off-by: Thiago Jung Bauermann <bauerman@linux.ibm.com> Message-Id: <20200826055535.951207-4-bauerman@linux.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2020-08-26 08:55:30 +03:00
/*
* All CPUs start halted. CPU0 is unhalted from the machine level reset code
* and the rest are explicitly started up by the guest using an RTAS call.
*/
cs->start_powered_off = true;
cs->cpu_index = cc->core_id + i;
if (!spapr_set_vcpu_id(cpu, cs->cpu_index, errp)) {
return NULL;
}
cpu->node_id = sc->node_id;
id = g_strdup_printf("thread[%d]", i);
qom: Drop parameter @errp of object_property_add() & friends The only way object_property_add() can fail is when a property with the same name already exists. Since our property names are all hardcoded, failure is a programming error, and the appropriate way to handle it is passing &error_abort. Same for its variants, except for object_property_add_child(), which additionally fails when the child already has a parent. Parentage is also under program control, so this is a programming error, too. We have a bit over 500 callers. Almost half of them pass &error_abort, slightly fewer ignore errors, one test case handles errors, and the remaining few callers pass them to their own callers. The previous few commits demonstrated once again that ignoring programming errors is a bad idea. Of the few ones that pass on errors, several violate the Error API. The Error ** argument must be NULL, &error_abort, &error_fatal, or a pointer to a variable containing NULL. Passing an argument of the latter kind twice without clearing it in between is wrong: if the first call sets an error, it no longer points to NULL for the second call. ich9_pm_add_properties(), sparc32_ledma_realize(), sparc32_dma_realize(), xilinx_axidma_realize(), xilinx_enet_realize() are wrong that way. When the one appropriate choice of argument is &error_abort, letting users pick the argument is a bad idea. Drop parameter @errp and assert the preconditions instead. There's one exception to "duplicate property name is a programming error": the way object_property_add() implements the magic (and undocumented) "automatic arrayification". Don't drop @errp there. Instead, rename object_property_add() to object_property_try_add(), and add the obvious wrapper object_property_add(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200505152926.18877-15-armbru@redhat.com> [Two semantic rebase conflicts resolved]
2020-05-05 18:29:22 +03:00
object_property_add_child(OBJECT(sc), id, obj);
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
cpu->machine_data = g_new0(SpaprCpuState, 1);
return cpu;
}
static void spapr_cpu_core_realize(DeviceState *dev, Error **errp)
{
/* We don't use SPAPR_MACHINE() in order to exit gracefully if the user
* tries to add a sPAPR CPU core to a non-pseries machine.
*/
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprMachineState *spapr =
(SpaprMachineState *) object_dynamic_cast(qdev_get_machine(),
TYPE_SPAPR_MACHINE);
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuCore *sc = SPAPR_CPU_CORE(OBJECT(dev));
CPUCore *cc = CPU_CORE(OBJECT(dev));
int i;
if (!spapr) {
error_setg(errp, TYPE_SPAPR_CPU_CORE " needs a pseries machine");
return;
}
qemu_register_reset(spapr_cpu_core_reset_handler, sc);
sc->threads = g_new0(PowerPCCPU *, cc->nr_threads);
for (i = 0; i < cc->nr_threads; i++) {
sc->threads[i] = spapr_create_vcpu(sc, i, errp);
if (!sc->threads[i] ||
!spapr_realize_vcpu(sc->threads[i], spapr, sc, errp)) {
spapr_cpu_core_unrealize(dev);
return;
}
}
}
static Property spapr_cpu_core_properties[] = {
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
DEFINE_PROP_INT32("node-id", SpaprCpuCore, node_id, CPU_UNSET_NUMA_NODE_ID),
DEFINE_PROP_BOOL("pre-3.0-migration", SpaprCpuCore, pre_3_0_migration,
false),
DEFINE_PROP_END_OF_LIST()
};
static void spapr_cpu_core_class_init(ObjectClass *oc, void *data)
{
DeviceClass *dc = DEVICE_CLASS(oc);
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
SpaprCpuCoreClass *scc = SPAPR_CPU_CORE_CLASS(oc);
dc->realize = spapr_cpu_core_realize;
dc->unrealize = spapr_cpu_core_unrealize;
dc->reset = spapr_cpu_core_reset;
device_class_set_props(dc, spapr_cpu_core_properties);
scc->cpu_type = data;
}
#define DEFINE_SPAPR_CPU_CORE_TYPE(cpu_model) \
{ \
.parent = TYPE_SPAPR_CPU_CORE, \
.class_data = (void *) POWERPC_CPU_TYPE_NAME(cpu_model), \
.class_init = spapr_cpu_core_class_init, \
.name = SPAPR_CPU_CORE_TYPE_NAME(cpu_model), \
}
static const TypeInfo spapr_cpu_core_type_infos[] = {
{
.name = TYPE_SPAPR_CPU_CORE,
.parent = TYPE_CPU_CORE,
.abstract = true,
spapr: Use CamelCase properly The qemu coding standard is to use CamelCase for type and structure names, and the pseries code follows that... sort of. There are quite a lot of places where we bend the rules in order to preserve the capitalization of internal acronyms like "PHB", "TCE", "DIMM" and most commonly "sPAPR". That was a bad idea - it frequently leads to names ending up with hard to read clusters of capital letters, and means they don't catch the eye as type identifiers, which is kind of the point of the CamelCase convention in the first place. In short, keeping type identifiers look like CamelCase is more important than preserving standard capitalization of internal "words". So, this patch renames a heap of spapr internal type names to a more standard CamelCase. In addition to case changes, we also make some other identifier renames: VIOsPAPR* -> SpaprVio* The reverse word ordering was only ever used to mitigate the capital cluster, so revert to the natural ordering. VIOsPAPRVTYDevice -> SpaprVioVty VIOsPAPRVLANDevice -> SpaprVioVlan Brevity, since the "Device" didn't add useful information sPAPRDRConnector -> SpaprDrc sPAPRDRConnectorClass -> SpaprDrcClass Brevity, and makes it clearer this is the same thing as a "DRC" mentioned in many other places in the code This is 100% a mechanical search-and-replace patch. It will, however, conflict with essentially any and all outstanding patches touching the spapr code. Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-03-06 07:35:37 +03:00
.instance_size = sizeof(SpaprCpuCore),
.class_size = sizeof(SpaprCpuCoreClass),
},
DEFINE_SPAPR_CPU_CORE_TYPE("970_v2.2"),
DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power5+_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power7_v2.3"),
DEFINE_SPAPR_CPU_CORE_TYPE("power7+_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power8_v2.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("power8e_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power8nvl_v1.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("power9_v1.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("power9_v2.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("power10_v1.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("power10_v2.0"),
#ifdef CONFIG_KVM
DEFINE_SPAPR_CPU_CORE_TYPE("host"),
#endif
};
DEFINE_TYPES(spapr_cpu_core_type_infos)