From: David Gibson <david@gibson.dropbear.id.au>
To: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: aik@au1.ibm.com, qemu-devel@nongnu.org, groug@kaod.org,
paulus@ozlabs.org, qemu-ppc@nongnu.org
Subject: Re: [Qemu-devel] [PATCH v10 4/6] target/ppc: Build rtas error log upon an MCE
Date: Wed, 3 Jul 2019 13:07:00 +1000 [thread overview]
Message-ID: <20190703030700.GH9442@umbus.fritz.box> (raw)
In-Reply-To: <80028d4d-88a7-4f90-f26d-52559857c66d@linux.vnet.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 12200 bytes --]
On Tue, Jul 02, 2019 at 03:19:24PM +0530, Aravinda Prasad wrote:
>
>
> On Tuesday 02 July 2019 09:33 AM, David Gibson wrote:
> > On Wed, Jun 12, 2019 at 02:51:21PM +0530, Aravinda Prasad wrote:
> >> Upon a machine check exception (MCE) in a guest address space,
> >> KVM causes a guest exit to enable QEMU to build and pass the
> >> error to the guest in the PAPR defined rtas error log format.
> >>
> >> This patch builds the rtas error log, copies it to the rtas_addr
> >> and then invokes the guest registered machine check handler. The
> >> handler in the guest takes suitable action(s) depending on the type
> >> and criticality of the error. For example, if an error is
> >> unrecoverable memory corruption in an application inside the
> >> guest, then the guest kernel sends a SIGBUS to the application.
> >> For recoverable errors, the guest performs recovery actions and
> >> logs the error.
> >>
> >> Signed-off-by: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
> >> ---
> >> hw/ppc/spapr.c | 13 +++
> >> hw/ppc/spapr_events.c | 238 ++++++++++++++++++++++++++++++++++++++++++++++++
> >> hw/ppc/spapr_rtas.c | 26 +++++
> >> include/hw/ppc/spapr.h | 6 +
> >> target/ppc/kvm.c | 4 +
> >> 5 files changed, 284 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> >> index 6cc2c3b..d61905b 100644
> >> --- a/hw/ppc/spapr.c
> >> +++ b/hw/ppc/spapr.c
> >> @@ -2908,6 +2908,19 @@ static void spapr_machine_init(MachineState *machine)
> >> error_report("Could not get size of LPAR rtas '%s'", filename);
> >> exit(1);
> >> }
> >> +
> >> + if (spapr_get_cap(spapr, SPAPR_CAP_FWNMI_MCE) == SPAPR_CAP_ON) {
> >> + /*
> >> + * Ensure that the rtas image size is less than RTAS_ERROR_LOG_OFFSET
> >> + * or else the rtas image will be overwritten with the rtas error log
> >> + * when a machine check exception is encountered.
> >> + */
> >> + g_assert(spapr->rtas_size < RTAS_ERROR_LOG_OFFSET);
> >> +
> >> + /* Resize rtas blob to accommodate error log */
> >> + spapr->rtas_size = RTAS_ERROR_LOG_MAX;
> >> + }
> >> +
> >> spapr->rtas_blob = g_malloc(spapr->rtas_size);
> >> if (load_image_size(filename, spapr->rtas_blob, spapr->rtas_size) < 0) {
> >> error_report("Could not load LPAR rtas '%s'", filename);
> >> diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
> >> index a0c66d7..51c052e 100644
> >> --- a/hw/ppc/spapr_events.c
> >> +++ b/hw/ppc/spapr_events.c
> >> @@ -212,6 +212,106 @@ struct hp_extended_log {
> >> struct rtas_event_log_v6_hp hp;
> >> } QEMU_PACKED;
> >>
> >> +struct rtas_event_log_v6_mc {
> >> +#define RTAS_LOG_V6_SECTION_ID_MC 0x4D43 /* MC */
> >> + struct rtas_event_log_v6_section_header hdr;
> >> + uint32_t fru_id;
> >> + uint32_t proc_id;
> >> + uint8_t error_type;
> >> +#define RTAS_LOG_V6_MC_TYPE_UE 0
> >> +#define RTAS_LOG_V6_MC_TYPE_SLB 1
> >> +#define RTAS_LOG_V6_MC_TYPE_ERAT 2
> >> +#define RTAS_LOG_V6_MC_TYPE_TLB 4
> >> +#define RTAS_LOG_V6_MC_TYPE_D_CACHE 5
> >> +#define RTAS_LOG_V6_MC_TYPE_I_CACHE 7
> >> + uint8_t sub_err_type;
> >> +#define RTAS_LOG_V6_MC_UE_INDETERMINATE 0
> >> +#define RTAS_LOG_V6_MC_UE_IFETCH 1
> >> +#define RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_IFETCH 2
> >> +#define RTAS_LOG_V6_MC_UE_LOAD_STORE 3
> >> +#define RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_LOAD_STORE 4
> >> +#define RTAS_LOG_V6_MC_SLB_PARITY 0
> >> +#define RTAS_LOG_V6_MC_SLB_MULTIHIT 1
> >> +#define RTAS_LOG_V6_MC_SLB_INDETERMINATE 2
> >> +#define RTAS_LOG_V6_MC_ERAT_PARITY 1
> >> +#define RTAS_LOG_V6_MC_ERAT_MULTIHIT 2
> >> +#define RTAS_LOG_V6_MC_ERAT_INDETERMINATE 3
> >> +#define RTAS_LOG_V6_MC_TLB_PARITY 1
> >> +#define RTAS_LOG_V6_MC_TLB_MULTIHIT 2
> >> +#define RTAS_LOG_V6_MC_TLB_INDETERMINATE 3
> >> + uint8_t reserved_1[6];
> >> + uint64_t effective_address;
> >> + uint64_t logical_address;
> >> +} QEMU_PACKED;
> >> +
> >> +struct mc_extended_log {
> >> + struct rtas_event_log_v6 v6hdr;
> >> + struct rtas_event_log_v6_mc mc;
> >> +} QEMU_PACKED;
> >> +
> >> +struct MC_ierror_table {
> >> + unsigned long srr1_mask;
> >> + unsigned long srr1_value;
> >> + bool nip_valid; /* nip is a valid indicator of faulting address */
> >> + uint8_t error_type;
> >> + uint8_t error_subtype;
> >> + unsigned int initiator;
> >> + unsigned int severity;
> >> +};
> >> +
> >> +static const struct MC_ierror_table mc_ierror_table[] = {
> >> +{ 0x00000000081c0000, 0x0000000000040000, true,
> >> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_IFETCH,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000000081c0000, 0x0000000000080000, true,
> >> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_PARITY,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000000081c0000, 0x00000000000c0000, true,
> >> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_MULTIHIT,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000000081c0000, 0x0000000000100000, true,
> >> + RTAS_LOG_V6_MC_TYPE_ERAT, RTAS_LOG_V6_MC_ERAT_MULTIHIT,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000000081c0000, 0x0000000000140000, true,
> >> + RTAS_LOG_V6_MC_TYPE_TLB, RTAS_LOG_V6_MC_TLB_MULTIHIT,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000000081c0000, 0x0000000000180000, true,
> >> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_IFETCH,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0, 0, 0, 0, 0, 0 } };
> >> +
> >> +struct MC_derror_table {
> >> + unsigned long dsisr_value;
> >> + bool dar_valid; /* dar is a valid indicator of faulting address */
> >> + uint8_t error_type;
> >> + uint8_t error_subtype;
> >> + unsigned int initiator;
> >> + unsigned int severity;
> >> +};
> >> +
> >> +static const struct MC_derror_table mc_derror_table[] = {
> >> +{ 0x00008000, false,
> >> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_LOAD_STORE,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00004000, true,
> >> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_LOAD_STORE,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000800, true,
> >> + RTAS_LOG_V6_MC_TYPE_ERAT, RTAS_LOG_V6_MC_ERAT_MULTIHIT,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000400, true,
> >> + RTAS_LOG_V6_MC_TYPE_TLB, RTAS_LOG_V6_MC_TLB_MULTIHIT,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000080, true,
> >> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_MULTIHIT, /* Before PARITY */
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0x00000100, true,
> >> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_PARITY,
> >> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
> >> +{ 0, false, 0, 0, 0, 0 } };
> >> +
> >> +#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42))
> >> +
> >> typedef enum EventClass {
> >> EVENT_CLASS_INTERNAL_ERRORS = 0,
> >> EVENT_CLASS_EPOW = 1,
> >> @@ -620,7 +720,141 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type,
> >> RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id);
> >> }
> >>
> >> -void spapr_mce_req_event(PowerPCCPU *cpu)
> >> +static uint32_t spapr_mce_get_elog_type(PowerPCCPU *cpu, bool recovered,
> >> + struct mc_extended_log *ext_elog)
> >> +{
> >> + int i;
> >> + CPUPPCState *env = &cpu->env;
> >> + uint32_t summary;
> >> + uint64_t dsisr = env->spr[SPR_DSISR];
> >> +
> >> + summary = RTAS_LOG_VERSION_6 | RTAS_LOG_OPTIONAL_PART_PRESENT;
> >> + if (recovered) {
> >> + summary |= RTAS_LOG_DISPOSITION_FULLY_RECOVERED;
> >> + } else {
> >> + summary |= RTAS_LOG_DISPOSITION_NOT_RECOVERED;
> >> + }
> >> +
> >> + if (SRR1_MC_LOADSTORE(env->spr[SPR_SRR1])) {
> >> + for (i = 0; mc_derror_table[i].dsisr_value; i++) {
> >> + if (!(dsisr & mc_derror_table[i].dsisr_value)) {
> >> + continue;
> >> + }
> >> +
> >> + ext_elog->mc.error_type = mc_derror_table[i].error_type;
> >> + ext_elog->mc.sub_err_type = mc_derror_table[i].error_subtype;
> >> + if (mc_derror_table[i].dar_valid) {
> >> + ext_elog->mc.effective_address = cpu_to_be64(env->spr[SPR_DAR]);
> >> + }
> >> +
> >> + summary |= mc_derror_table[i].initiator
> >> + | mc_derror_table[i].severity;
> >> +
> >> + return summary;
> >> + }
> >> + } else {
> >> + for (i = 0; mc_ierror_table[i].srr1_mask; i++) {
> >> + if ((env->spr[SPR_SRR1] & mc_ierror_table[i].srr1_mask) !=
> >> + mc_ierror_table[i].srr1_value) {
> >> + continue;
> >> + }
> >> +
> >> + ext_elog->mc.error_type = mc_ierror_table[i].error_type;
> >> + ext_elog->mc.sub_err_type = mc_ierror_table[i].error_subtype;
> >> + if (mc_ierror_table[i].nip_valid) {
> >> + ext_elog->mc.effective_address = cpu_to_be64(env->nip);
> >> + }
> >> +
> >> + summary |= mc_ierror_table[i].initiator
> >> + | mc_ierror_table[i].severity;
> >> +
> >> + return summary;
> >> + }
> >> + }
> >> +
> >> + summary |= RTAS_LOG_INITIATOR_CPU;
> >> + return summary;
> >> +}
> >> +
> >> +static void spapr_mce_dispatch_elog(PowerPCCPU *cpu, bool recovered)
> >> +{
> >> + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
> >> + CPUState *cs = CPU(cpu);
> >> + uint64_t rtas_addr;
> >> + CPUPPCState *env = &cpu->env;
> >> + PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
> >> + target_ulong r3, msr = 0;
> >> + struct rtas_error_log log;
> >> + struct mc_extended_log *ext_elog;
> >> + uint32_t summary;
> >> +
> >> + /*
> >> + * Properly set bits in MSR before we invoke the handler.
> >> + * SRR0/1, DAR and DSISR are properly set by KVM
> >> + */
> >> + if (!(*pcc->interrupts_big_endian)(cpu)) {
> >> + msr |= (1ULL << MSR_LE);
> >> + }
> >> +
> >> + if (env->msr & (1ULL << MSR_SF)) {
> >> + msr |= (1ULL << MSR_SF);
> >> + }
> >> +
> >> + msr |= (1ULL << MSR_ME);
> >> +
> >> + if (spapr->guest_machine_check_addr == -1) {
> >> + /*
> >> + * This implies that we have hit a machine check between system
> >> + * reset and "ibm,nmi-register". Fall back to the old machine
> >> + * check behavior in such cases.
> >> + */
> >> + env->spr[SPR_SRR0] = env->nip;
> >> + env->spr[SPR_SRR1] = env->msr;
> >> + env->msr = msr;
> >> + env->nip = 0x200;
> >> + return;
> >
> > Hm, does this differ from what ppc_cpu_do_system_reset() will do?
>
> Not much, but we branch to 0x200 instead of 0x100. But I think calling
>
> powerpc_excp(cpu, env->excp_model, POWERPC_EXCP_MCHECK)
>
> should also work. Let me if you prefer using powerpc_excp().
Yes, I'd prefer to share code with existing exception paths where
possible.
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2019-07-03 6:14 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-12 9:20 [Qemu-devel] [PATCH v10 0/6] target-ppc/spapr: Add FWNMI support in QEMU for PowerKVM guests Aravinda Prasad
2019-06-12 9:20 ` [Qemu-devel] [PATCH v10 1/6] Wrapper function to wait on condition for the main loop mutex Aravinda Prasad
2019-06-12 9:21 ` [Qemu-devel] [PATCH v10 2/6] ppc: spapr: Introduce FWNMI capability Aravinda Prasad
2019-07-02 3:51 ` David Gibson
2019-07-02 6:24 ` Aravinda Prasad
2019-07-03 3:03 ` David Gibson
2019-07-03 9:28 ` Aravinda Prasad
2019-07-04 1:07 ` David Gibson
2019-07-04 5:03 ` Aravinda Prasad
2019-07-05 1:07 ` David Gibson
2019-07-05 11:19 ` Aravinda Prasad
2019-07-05 13:23 ` [Qemu-devel] [Qemu-ppc] " Greg Kurz
2019-07-08 10:26 ` Aravinda Prasad
2019-06-12 9:21 ` [Qemu-devel] [PATCH v10 3/6] target/ppc: Handle NMI guest exit Aravinda Prasad
2019-07-02 3:52 ` David Gibson
2019-06-12 9:21 ` [Qemu-devel] [PATCH v10 4/6] target/ppc: Build rtas error log upon an MCE Aravinda Prasad
2019-07-02 4:03 ` David Gibson
2019-07-02 9:49 ` Aravinda Prasad
2019-07-03 3:07 ` David Gibson [this message]
2019-07-03 7:16 ` Aravinda Prasad
2019-06-12 9:21 ` [Qemu-devel] [PATCH v10 5/6] migration: Include migration support for machine check handling Aravinda Prasad
2019-06-12 9:21 ` [Qemu-devel] [PATCH v10 6/6] ppc: spapr: Handle "ibm, nmi-register" and "ibm, nmi-interlock" RTAS calls Aravinda Prasad
2019-06-24 14:29 ` Greg Kurz
2019-06-25 6:16 ` Aravinda Prasad
2019-06-25 7:00 ` Greg Kurz
2019-06-26 5:13 ` [Qemu-devel] [Qemu-ppc] " Aravinda Prasad
2019-07-02 4:12 ` David Gibson
2019-07-02 4:11 ` [Qemu-devel] " David Gibson
2019-07-02 10:40 ` Aravinda Prasad
2019-07-03 3:20 ` David Gibson
2019-07-03 9:00 ` Aravinda Prasad
2019-07-04 1:12 ` David Gibson
2019-07-04 5:19 ` Aravinda Prasad
2019-07-04 18:37 ` [Qemu-devel] [Qemu-ppc] " Greg Kurz
2019-07-05 11:11 ` Aravinda Prasad
2019-07-05 12:35 ` Greg Kurz
2019-07-09 6:41 ` [Qemu-devel] " David Gibson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190703030700.GH9442@umbus.fritz.box \
--to=david@gibson.dropbear.id.au \
--cc=aik@au1.ibm.com \
--cc=aravinda@linux.vnet.ibm.com \
--cc=groug@kaod.org \
--cc=paulus@ozlabs.org \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).