| Message ID | 20210707003314.37110-3-danielhb413@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | DEVICE_UNPLUG_ERROR QAPI event | expand |
On Tue, 6 Jul 2021 21:33:13 -0300 Daniel Henrique Barboza <danielhb413@gmail.com> wrote: > Linux Kernel 5.12 is now unisolating CPU DRCs in the device_removal > error path, signalling that the hotunplug process wasn't successful. > This allow us to send a DEVICE_UNPLUG_ERROR in drc_unisolate_logical() > to signal this error to the management layer. > > We also have another error path in spapr_memory_unplug_rollback() for > configured LMB DRCs. Kernels older than 5.13 will not unisolate the LMBs > in the hotunplug error path, but it will reconfigure them. Let's send > the DEVICE_UNPLUG_ERROR event in that code path as well to cover the > case of older kernels. > > Reviewed-by: David Gibson <david@gibson.dropbear.id.au> > Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> > --- Reviewed-by: Greg Kurz <groug@kaod.org> > hw/ppc/spapr.c | 8 ++++++++ > hw/ppc/spapr_drc.c | 15 +++++++++------ > 2 files changed, 17 insertions(+), 6 deletions(-) > > diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c > index 4dd90b75cc..fc071a1767 100644 > --- a/hw/ppc/spapr.c > +++ b/hw/ppc/spapr.c > @@ -29,6 +29,7 @@ > #include "qemu/datadir.h" > #include "qapi/error.h" > #include "qapi/qapi-events-machine.h" > +#include "qapi/qapi-events-qdev.h" > #include "qapi/visitor.h" > #include "sysemu/sysemu.h" > #include "sysemu/hostmem.h" > @@ -3641,7 +3642,14 @@ void spapr_memory_unplug_rollback(SpaprMachineState *spapr, DeviceState *dev) > */ > qapi_error = g_strdup_printf("Memory hotunplug rejected by the guest " > "for device %s", dev->id); > + > + /* > + * Send both MEM_UNPLUG_ERROR and DEVICE_UNPLUG_ERROR > + * while the deprecation of MEM_UNPLUG_ERROR is > + * pending. > + */ > qapi_event_send_mem_unplug_error(dev->id, qapi_error); > + qapi_event_send_device_unplug_error(dev->id, qapi_error); > } > > /* Callback to be called during DRC release. */ > diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c > index a2f2634601..45a7b1aa16 100644 > --- a/hw/ppc/spapr_drc.c > +++ b/hw/ppc/spapr_drc.c > @@ -17,6 +17,8 @@ > #include "hw/ppc/spapr_drc.h" > #include "qom/object.h" > #include "migration/vmstate.h" > +#include "qapi/error.h" > +#include "qapi/qapi-events-qdev.h" > #include "qapi/visitor.h" > #include "qemu/error-report.h" > #include "hw/ppc/spapr.h" /* for RTAS return codes */ > @@ -160,6 +162,10 @@ static uint32_t drc_unisolate_logical(SpaprDrc *drc) > * means that the kernel is refusing the removal. > */ > if (drc->unplug_requested && drc->dev) { > + const char qapi_error_fmt[] = "Device hotunplug rejected by the " > + "guest for device %s"; > + g_autofree char *qapi_error = NULL; > + > if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB) { > spapr = SPAPR_MACHINE(qdev_get_machine()); > > @@ -167,13 +173,10 @@ static uint32_t drc_unisolate_logical(SpaprDrc *drc) > } > > drc->unplug_requested = false; > - error_report("Device hotunplug rejected by the guest " > - "for device %s", drc->dev->id); > + error_report(qapi_error_fmt, drc->dev->id); > > - /* > - * TODO: send a QAPI DEVICE_UNPLUG_ERROR event when > - * it is implemented. > - */ > + qapi_error = g_strdup_printf(qapi_error_fmt, drc->dev->id); > + qapi_event_send_device_unplug_error(drc->dev->id, qapi_error); > } > > return RTAS_OUT_SUCCESS; /* Nothing to do */
Daniel Henrique Barboza <danielhb413@gmail.com> writes: > Linux Kernel 5.12 is now unisolating CPU DRCs in the device_removal > error path, signalling that the hotunplug process wasn't successful. > This allow us to send a DEVICE_UNPLUG_ERROR in drc_unisolate_logical() > to signal this error to the management layer. > > We also have another error path in spapr_memory_unplug_rollback() for > configured LMB DRCs. Kernels older than 5.13 will not unisolate the LMBs > in the hotunplug error path, but it will reconfigure them. Let's send > the DEVICE_UNPLUG_ERROR event in that code path as well to cover the > case of older kernels. > > Reviewed-by: David Gibson <david@gibson.dropbear.id.au> > Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> > --- > hw/ppc/spapr.c | 8 ++++++++ > hw/ppc/spapr_drc.c | 15 +++++++++------ > 2 files changed, 17 insertions(+), 6 deletions(-) > > diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c > index 4dd90b75cc..fc071a1767 100644 > --- a/hw/ppc/spapr.c > +++ b/hw/ppc/spapr.c > @@ -29,6 +29,7 @@ > #include "qemu/datadir.h" > #include "qapi/error.h" > #include "qapi/qapi-events-machine.h" > +#include "qapi/qapi-events-qdev.h" > #include "qapi/visitor.h" > #include "sysemu/sysemu.h" > #include "sysemu/hostmem.h" > @@ -3641,7 +3642,14 @@ void spapr_memory_unplug_rollback(SpaprMachineState *spapr, DeviceState *dev) > */ > qapi_error = g_strdup_printf("Memory hotunplug rejected by the guest " > "for device %s", dev->id); > + > + /* > + * Send both MEM_UNPLUG_ERROR and DEVICE_UNPLUG_ERROR > + * while the deprecation of MEM_UNPLUG_ERROR is > + * pending. > + */ > qapi_event_send_mem_unplug_error(dev->id, qapi_error); > + qapi_event_send_device_unplug_error(dev->id, qapi_error); Can dev->id be null here? Such devices exist, but maybe not here. If dev->id can be null, we pass null to qapi_event_send_device_unplug_error(), which is not okay. The output visitor papers over by replacing with "". Let's not rely on this misfeature. > } > > /* Callback to be called during DRC release. */ > diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c > index a2f2634601..45a7b1aa16 100644 > --- a/hw/ppc/spapr_drc.c > +++ b/hw/ppc/spapr_drc.c > @@ -17,6 +17,8 @@ > #include "hw/ppc/spapr_drc.h" > #include "qom/object.h" > #include "migration/vmstate.h" > +#include "qapi/error.h" > +#include "qapi/qapi-events-qdev.h" > #include "qapi/visitor.h" > #include "qemu/error-report.h" > #include "hw/ppc/spapr.h" /* for RTAS return codes */ > @@ -160,6 +162,10 @@ static uint32_t drc_unisolate_logical(SpaprDrc *drc) > * means that the kernel is refusing the removal. > */ > if (drc->unplug_requested && drc->dev) { > + const char qapi_error_fmt[] = "Device hotunplug rejected by the " > + "guest for device %s"; > + g_autofree char *qapi_error = NULL; > + > if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB) { > spapr = SPAPR_MACHINE(qdev_get_machine()); > > @@ -167,13 +173,10 @@ static uint32_t drc_unisolate_logical(SpaprDrc *drc) > } > > drc->unplug_requested = false; > - error_report("Device hotunplug rejected by the guest " > - "for device %s", drc->dev->id); > + error_report(qapi_error_fmt, drc->dev->id); > > - /* > - * TODO: send a QAPI DEVICE_UNPLUG_ERROR event when > - * it is implemented. > - */ > + qapi_error = g_strdup_printf(qapi_error_fmt, drc->dev->id); > + qapi_event_send_device_unplug_error(drc->dev->id, qapi_error); > } > > return RTAS_OUT_SUCCESS; /* Nothing to do */ Likewise, only here we also pass it to g_strdup_printf() and possibly vprintf() via error_report(). Null arguments to %s crash on some systems. The issue predates your patch. I'm not sure reporting failed unplug with error_report() is a good idea, but it's not your patch's idea.
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 4dd90b75cc..fc071a1767 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -29,6 +29,7 @@ #include "qemu/datadir.h" #include "qapi/error.h" #include "qapi/qapi-events-machine.h" +#include "qapi/qapi-events-qdev.h" #include "qapi/visitor.h" #include "sysemu/sysemu.h" #include "sysemu/hostmem.h" @@ -3641,7 +3642,14 @@ void spapr_memory_unplug_rollback(SpaprMachineState *spapr, DeviceState *dev) */ qapi_error = g_strdup_printf("Memory hotunplug rejected by the guest " "for device %s", dev->id); + + /* + * Send both MEM_UNPLUG_ERROR and DEVICE_UNPLUG_ERROR + * while the deprecation of MEM_UNPLUG_ERROR is + * pending. + */ qapi_event_send_mem_unplug_error(dev->id, qapi_error); + qapi_event_send_device_unplug_error(dev->id, qapi_error); } /* Callback to be called during DRC release. */ diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c index a2f2634601..45a7b1aa16 100644 --- a/hw/ppc/spapr_drc.c +++ b/hw/ppc/spapr_drc.c @@ -17,6 +17,8 @@ #include "hw/ppc/spapr_drc.h" #include "qom/object.h" #include "migration/vmstate.h" +#include "qapi/error.h" +#include "qapi/qapi-events-qdev.h" #include "qapi/visitor.h" #include "qemu/error-report.h" #include "hw/ppc/spapr.h" /* for RTAS return codes */ @@ -160,6 +162,10 @@ static uint32_t drc_unisolate_logical(SpaprDrc *drc) * means that the kernel is refusing the removal. */ if (drc->unplug_requested && drc->dev) { + const char qapi_error_fmt[] = "Device hotunplug rejected by the " + "guest for device %s"; + g_autofree char *qapi_error = NULL; + if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB) { spapr = SPAPR_MACHINE(qdev_get_machine()); @@ -167,13 +173,10 @@ static uint32_t drc_unisolate_logical(SpaprDrc *drc) } drc->unplug_requested = false; - error_report("Device hotunplug rejected by the guest " - "for device %s", drc->dev->id); + error_report(qapi_error_fmt, drc->dev->id); - /* - * TODO: send a QAPI DEVICE_UNPLUG_ERROR event when - * it is implemented. - */ + qapi_error = g_strdup_printf(qapi_error_fmt, drc->dev->id); + qapi_event_send_device_unplug_error(drc->dev->id, qapi_error); } return RTAS_OUT_SUCCESS; /* Nothing to do */