qemu/hw/ppc/spapr_drc.c

1238 lines
38 KiB
C
Raw Normal View History

/*
* QEMU SPAPR Dynamic Reconfiguration Connector Implementation
*
* Copyright IBM Corp. 2014
*
* Authors:
* Michael Roth <mdroth@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"
2016-03-14 11:01:28 +03:00
#include "qapi/error.h"
#include "qapi/qmp/qnull.h"
#include "cpu.h"
#include "qemu/cutils.h"
#include "hw/ppc/spapr_drc.h"
#include "qom/object.h"
#include "hw/qdev.h"
#include "qapi/visitor.h"
#include "qemu/error-report.h"
#include "hw/ppc/spapr.h" /* for RTAS return codes */
#include "hw/pci-host/spapr.h" /* spapr_phb_remove_pci_device_cb callback */
spapr_drc: Allow FDT fragment to be added later The current logic is to provide the FDT fragment when attaching a device to a DRC. This works perfectly fine for our current hotplug support, but soon we will add support for PHB hotplug which has some constraints, that CPU, PCI and LMB devices don't seem to have. The first constraint is that the "ibm,dma-window" property of the PHB node requires the IOMMU to be configured, ie, spapr_tce_table_enable() has been called, which happens during PHB reset. It is okay in the case of hotplug since the device is reset before the hotplug handler is called. On the contrary with coldplug, the hotplug handler is called first and device is only reset during the initial system reset. Trying to create the FDT fragment on the hotplug path in this case, would result in somthing like this: ibm,dma-window = < 0x80000000 0x00 0x00 0x00 0x00 >; This will cause linux in the guest to panic, by simply removing and re-adding the PHB using the drmgr command: page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz)); if (!page) panic("iommu_init_table: Can't allocate %ld bytes\n", sz); The second and maybe more problematic constraint is that the "interrupt-map" property needs to reference the interrupt controller node using the very same phandle that SLOF has already exposed to the guest. QEMU requires SLOF to call the private KVMPPC_H_UPDATE_DT hcall at some point to know about this phandle. With the latest QEMU and SLOF, this happens when SLOF gets quiesced. This means that if the PHB gets hotplugged after CAS but before SLOF quiesce, then we're sure that the phandle is not known when the hotplug handler is called. The FDT is only needed when the guest first invokes RTAS to configure the connector actually, long after SLOF quiesce. Let's postpone the creation of FDT fragments for PHBs to rtas_ibm_configure_connector(). Since we only need this for PHBs, introduce a new method in the base DRC class for that. DRC subtypes will be converted to use it in subsequent patches. Allow spapr_drc_attach() to be passed a NULL fdt argument if the method is available. When all DRC subtypes have been converted, the fdt argument will eventually disappear. Signed-off-by: Greg Kurz <groug@kaod.org> Message-Id: <155059665823.1466090.18358845122627355537.stgit@bahia.lab.toulouse-stg.fr.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-02-19 20:17:38 +03:00
#include "sysemu/device_tree.h"
#include "trace.h"
#define DRC_CONTAINER_PATH "/dr-connector"
#define DRC_INDEX_TYPE_SHIFT 28
#define DRC_INDEX_ID_MASK ((1ULL << DRC_INDEX_TYPE_SHIFT) - 1)
sPAPRDRConnectorType spapr_drc_type(sPAPRDRConnector *drc)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
return 1 << drck->typeshift;
}
uint32_t spapr_drc_index(sPAPRDRConnector *drc)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
/* no set format for a drc index: it only needs to be globally
* unique. this is how we encode the DRC type on bare-metal
* however, so might as well do that here
*/
return (drck->typeshift << DRC_INDEX_TYPE_SHIFT)
| (drc->id & DRC_INDEX_ID_MASK);
}
static uint32_t drc_isolate_physical(sPAPRDRConnector *drc)
{
switch (drc->state) {
case SPAPR_DRC_STATE_PHYSICAL_POWERON:
return RTAS_OUT_SUCCESS; /* Nothing to do */
case SPAPR_DRC_STATE_PHYSICAL_CONFIGURED:
break; /* see below */
case SPAPR_DRC_STATE_PHYSICAL_UNISOLATE:
return RTAS_OUT_PARAM_ERROR; /* not allowed */
default:
g_assert_not_reached();
}
drc->state = SPAPR_DRC_STATE_PHYSICAL_POWERON;
if (drc->unplug_requested) {
uint32_t drc_index = spapr_drc_index(drc);
trace_spapr_drc_set_isolation_state_finalizing(drc_index);
spapr_drc_detach(drc);
}
return RTAS_OUT_SUCCESS;
}
static uint32_t drc_unisolate_physical(sPAPRDRConnector *drc)
{
switch (drc->state) {
case SPAPR_DRC_STATE_PHYSICAL_UNISOLATE:
case SPAPR_DRC_STATE_PHYSICAL_CONFIGURED:
return RTAS_OUT_SUCCESS; /* Nothing to do */
case SPAPR_DRC_STATE_PHYSICAL_POWERON:
break; /* see below */
default:
g_assert_not_reached();
}
/* cannot unisolate a non-existent resource, and, or resources
* which are in an 'UNUSABLE' allocation state. (PAPR 2.7,
* 13.5.3.5)
*/
if (!drc->dev) {
return RTAS_OUT_NO_SUCH_INDICATOR;
}
drc->state = SPAPR_DRC_STATE_PHYSICAL_UNISOLATE;
spapr: Remove sPAPRConfigureConnectorState sub-structure Most of the time, the state of a DRC object is contained in the single 'state' variable. However, during the transition from UNISOLATE to CONFIGURED state requires multiple calls to the ibm,configure-connector RTAS call to retrieve the device tree for the attached device. We need some extra state to keep track of where we're up to in delivering the device tree information to the guest. Currently that extra state is in a sPAPRConfigureConnectorState substructure which is only allocated when we're in the middle of the configure connector process. That sounds like a good idea, but the extra state is only two integers - on many platforms that will take up the same room as the (maybe NULL) ccs pointer even before malloc() overhead. Plus it's another object whose lifetime we need to manage. In short, it's not worth it. So, fold the sPAPRConfigureConnectorState substructure directly into the DRC object. Previously the structure was allocated lazily when the configure-connector call discovers it's not there. Now, we need to initialize the subfields pre-emptively, as soon as we enter UNISOLATE state. Although it's not strictly necessary (the field values should only ever be consulted when in UNISOLATE state), we try to keep them at -1 when in other states, as a debugging aid. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Daniel Barboza <danielhb@linux.vnet.ibm.com> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-21 12:12:14 +03:00
drc->ccs_offset = drc->fdt_start_offset;
drc->ccs_depth = 0;
return RTAS_OUT_SUCCESS;
}
static uint32_t drc_isolate_logical(sPAPRDRConnector *drc)
{
switch (drc->state) {
case SPAPR_DRC_STATE_LOGICAL_AVAILABLE:
case SPAPR_DRC_STATE_LOGICAL_UNUSABLE:
return RTAS_OUT_SUCCESS; /* Nothing to do */
case SPAPR_DRC_STATE_LOGICAL_CONFIGURED:
break; /* see below */
case SPAPR_DRC_STATE_LOGICAL_UNISOLATE:
return RTAS_OUT_PARAM_ERROR; /* not allowed */
default:
g_assert_not_reached();
}
/*
* Fail any requests to ISOLATE the LMB DRC if this LMB doesn't
* belong to a DIMM device that is marked for removal.
*
* Currently the guest userspace tool drmgr that drives the memory
* hotplug/unplug will just try to remove a set of 'removable' LMBs
* in response to a hot unplug request that is based on drc-count.
* If the LMB being removed doesn't belong to a DIMM device that is
* actually being unplugged, fail the isolation request here.
*/
if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB
&& !drc->unplug_requested) {
return RTAS_OUT_HW_ERROR;
}
drc->state = SPAPR_DRC_STATE_LOGICAL_AVAILABLE;
/* if we're awaiting release, but still in an unconfigured state,
* it's likely the guest is still in the process of configuring
* the device and is transitioning the devices to an ISOLATED
* state as a part of that process. so we only complete the
* removal when this transition happens for a device in a
* configured state, as suggested by the state diagram from PAPR+
* 2.7, 13.4
*/
if (drc->unplug_requested) {
uint32_t drc_index = spapr_drc_index(drc);
trace_spapr_drc_set_isolation_state_finalizing(drc_index);
spapr_drc_detach(drc);
}
return RTAS_OUT_SUCCESS;
}
static uint32_t drc_unisolate_logical(sPAPRDRConnector *drc)
{
switch (drc->state) {
case SPAPR_DRC_STATE_LOGICAL_UNISOLATE:
case SPAPR_DRC_STATE_LOGICAL_CONFIGURED:
return RTAS_OUT_SUCCESS; /* Nothing to do */
case SPAPR_DRC_STATE_LOGICAL_AVAILABLE:
break; /* see below */
case SPAPR_DRC_STATE_LOGICAL_UNUSABLE:
return RTAS_OUT_NO_SUCH_INDICATOR; /* not allowed */
default:
g_assert_not_reached();
}
/* Move to AVAILABLE state should have ensured device was present */
g_assert(drc->dev);
drc->state = SPAPR_DRC_STATE_LOGICAL_UNISOLATE;
spapr: Remove sPAPRConfigureConnectorState sub-structure Most of the time, the state of a DRC object is contained in the single 'state' variable. However, during the transition from UNISOLATE to CONFIGURED state requires multiple calls to the ibm,configure-connector RTAS call to retrieve the device tree for the attached device. We need some extra state to keep track of where we're up to in delivering the device tree information to the guest. Currently that extra state is in a sPAPRConfigureConnectorState substructure which is only allocated when we're in the middle of the configure connector process. That sounds like a good idea, but the extra state is only two integers - on many platforms that will take up the same room as the (maybe NULL) ccs pointer even before malloc() overhead. Plus it's another object whose lifetime we need to manage. In short, it's not worth it. So, fold the sPAPRConfigureConnectorState substructure directly into the DRC object. Previously the structure was allocated lazily when the configure-connector call discovers it's not there. Now, we need to initialize the subfields pre-emptively, as soon as we enter UNISOLATE state. Although it's not strictly necessary (the field values should only ever be consulted when in UNISOLATE state), we try to keep them at -1 when in other states, as a debugging aid. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Daniel Barboza <danielhb@linux.vnet.ibm.com> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-21 12:12:14 +03:00
drc->ccs_offset = drc->fdt_start_offset;
drc->ccs_depth = 0;
return RTAS_OUT_SUCCESS;
}
static uint32_t drc_set_usable(sPAPRDRConnector *drc)
{
switch (drc->state) {
case SPAPR_DRC_STATE_LOGICAL_AVAILABLE:
case SPAPR_DRC_STATE_LOGICAL_UNISOLATE:
case SPAPR_DRC_STATE_LOGICAL_CONFIGURED:
return RTAS_OUT_SUCCESS; /* Nothing to do */
case SPAPR_DRC_STATE_LOGICAL_UNUSABLE:
break; /* see below */
default:
g_assert_not_reached();
}
/* if there's no resource/device associated with the DRC, there's
* no way for us to put it in an allocation state consistent with
* being 'USABLE'. PAPR 2.7, 13.5.3.4 documents that this should
* result in an RTAS return code of -3 / "no such indicator"
*/
if (!drc->dev) {
return RTAS_OUT_NO_SUCH_INDICATOR;
}
if (drc->unplug_requested) {
/* Don't allow the guest to move a device away from UNUSABLE
* state when we want to unplug it */
return RTAS_OUT_NO_SUCH_INDICATOR;
}
drc->state = SPAPR_DRC_STATE_LOGICAL_AVAILABLE;
return RTAS_OUT_SUCCESS;
}
static uint32_t drc_set_unusable(sPAPRDRConnector *drc)
{
switch (drc->state) {
case SPAPR_DRC_STATE_LOGICAL_UNUSABLE:
return RTAS_OUT_SUCCESS; /* Nothing to do */
case SPAPR_DRC_STATE_LOGICAL_AVAILABLE:
break; /* see below */
case SPAPR_DRC_STATE_LOGICAL_UNISOLATE:
case SPAPR_DRC_STATE_LOGICAL_CONFIGURED:
return RTAS_OUT_NO_SUCH_INDICATOR; /* not allowed */
default:
g_assert_not_reached();
}
drc->state = SPAPR_DRC_STATE_LOGICAL_UNUSABLE;
if (drc->unplug_requested) {
uint32_t drc_index = spapr_drc_index(drc);
trace_spapr_drc_set_allocation_state_finalizing(drc_index);
spapr_drc_detach(drc);
}
return RTAS_OUT_SUCCESS;
}
static const char *spapr_drc_name(sPAPRDRConnector *drc)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
/* human-readable name for a DRC to encode into the DT
* description. this is mainly only used within a guest in place
* of the unique DRC index.
*
* in the case of VIO/PCI devices, it corresponds to a "location
* code" that maps a logical device/function (DRC index) to a
* physical (or virtual in the case of VIO) location in the system
* by chaining together the "location label" for each
* encapsulating component.
*
* since this is more to do with diagnosing physical hardware
* issues than guest compatibility, we choose location codes/DRC
* names that adhere to the documented format, but avoid encoding
* the entire topology information into the label/code, instead
* just using the location codes based on the labels for the
* endpoints (VIO/PCI adaptor connectors), which is basically just
* "C" followed by an integer ID.
*
* DRC names as documented by PAPR+ v2.7, 13.5.2.4
* location codes as documented by PAPR+ v2.7, 12.3.1.5
*/
return g_strdup_printf("%s%d", drck->drc_name_prefix, drc->id);
}
/*
* dr-entity-sense sensor value
* returned via get-sensor-state RTAS calls
* as expected by state diagram in PAPR+ 2.7, 13.4
* based on the current allocation/indicator/power states
* for the DR connector.
*/
static sPAPRDREntitySense physical_entity_sense(sPAPRDRConnector *drc)
{
/* this assumes all PCI devices are assigned to a 'live insertion'
* power domain, where QEMU manages power state automatically as
* opposed to the guest. present, non-PCI resources are unaffected
* by power state.
*/
return drc->dev ? SPAPR_DR_ENTITY_SENSE_PRESENT
: SPAPR_DR_ENTITY_SENSE_EMPTY;
}
static sPAPRDREntitySense logical_entity_sense(sPAPRDRConnector *drc)
{
switch (drc->state) {
case SPAPR_DRC_STATE_LOGICAL_UNUSABLE:
return SPAPR_DR_ENTITY_SENSE_UNUSABLE;
case SPAPR_DRC_STATE_LOGICAL_AVAILABLE:
case SPAPR_DRC_STATE_LOGICAL_UNISOLATE:
case SPAPR_DRC_STATE_LOGICAL_CONFIGURED:
g_assert(drc->dev);
return SPAPR_DR_ENTITY_SENSE_PRESENT;
default:
g_assert_not_reached();
}
}
static void prop_get_index(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj);
uint32_t value = spapr_drc_index(drc);
qapi: Swap visit_* arguments for consistent 'name' placement JSON uses "name":value, but many of our visitor interfaces were called with visit_type_FOO(v, &value, name, errp). This can be a bit confusing to have to mentally swap the parameter order to match JSON order. It's particularly bad for visit_start_struct(), where the 'name' parameter is smack in the middle of the otherwise-related group of 'obj, kind, size' parameters! It's time to do a global swap of the parameter ordering, so that the 'name' parameter is always immediately after the Visitor argument. Additional reason in favor of the swap: the existing include/qjson.h prefers listing 'name' first in json_prop_*(), and I have plans to unify that file with the qapi visitors; listing 'name' first in qapi will minimize churn to the (admittedly few) qjson.h clients. Later patches will then fix docs, object.h, visitor-impl.h, and those clients to match. Done by first patching scripts/qapi*.py by hand to make generated files do what I want, then by running the following Coccinelle script to affect the rest of the code base: $ spatch --sp-file script `git grep -l '\bvisit_' -- '**/*.[ch]'` I then had to apply some touchups (Coccinelle insisted on TAB indentation in visitor.h, and botched the signature of visit_type_enum() by rewriting 'const char *const strings[]' to the syntactically invalid 'const char*const[] strings'). The movement of parameters is sufficient to provoke compiler errors if any callers were missed. // Part 1: Swap declaration order @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_start_struct -(TV v, TObj OBJ, T1 ARG1, const char *name, T2 ARG2, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type bool, TV, T1; identifier ARG1; @@ bool visit_optional -(TV v, T1 ARG1, const char *name) +(TV v, const char *name, T1 ARG1) { ... } @@ type TV, TErr, TObj, T1; identifier OBJ, ARG1; @@ void visit_get_next_type -(TV v, TObj OBJ, T1 ARG1, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, TErr errp) { ... } @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_type_enum -(TV v, TObj OBJ, T1 ARG1, T2 ARG2, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type TV, TErr, TObj; identifier OBJ; identifier VISIT_TYPE =~ "^visit_type_"; @@ void VISIT_TYPE -(TV v, TObj OBJ, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, TErr errp) { ... } // Part 2: swap caller order @@ expression V, NAME, OBJ, ARG1, ARG2, ERR; identifier VISIT_TYPE =~ "^visit_type_"; @@ ( -visit_start_struct(V, OBJ, ARG1, NAME, ARG2, ERR) +visit_start_struct(V, NAME, OBJ, ARG1, ARG2, ERR) | -visit_optional(V, ARG1, NAME) +visit_optional(V, NAME, ARG1) | -visit_get_next_type(V, OBJ, ARG1, NAME, ERR) +visit_get_next_type(V, NAME, OBJ, ARG1, ERR) | -visit_type_enum(V, OBJ, ARG1, ARG2, NAME, ERR) +visit_type_enum(V, NAME, OBJ, ARG1, ARG2, ERR) | -VISIT_TYPE(V, OBJ, NAME, ERR) +VISIT_TYPE(V, NAME, OBJ, ERR) ) Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-Id: <1454075341-13658-19-git-send-email-eblake@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-01-29 16:48:54 +03:00
visit_type_uint32(v, name, &value, errp);
}
static void prop_get_fdt(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj);
QNull *null = NULL;
Error *err = NULL;
int fdt_offset_next, fdt_offset, fdt_depth;
void *fdt;
if (!drc->fdt) {
visit_type_null(v, NULL, &null, errp);
qobject_unref(null);
return;
}
fdt = drc->fdt;
fdt_offset = drc->fdt_start_offset;
fdt_depth = 0;
do {
const char *name = NULL;
const struct fdt_property *prop = NULL;
int prop_len = 0, name_len = 0;
uint32_t tag;
tag = fdt_next_tag(fdt, fdt_offset, &fdt_offset_next);
switch (tag) {
case FDT_BEGIN_NODE:
fdt_depth++;
name = fdt_get_name(fdt, fdt_offset, &name_len);
visit_start_struct(v, name, NULL, 0, &err);
if (err) {
error_propagate(errp, err);
return;
}
break;
case FDT_END_NODE:
/* shouldn't ever see an FDT_END_NODE before FDT_BEGIN_NODE */
g_assert(fdt_depth > 0);
qapi: Split visit_end_struct() into pieces As mentioned in previous patches, we want to call visit_end_struct() functions unconditionally, so that visitors can release resources tied up since the matching visit_start_struct() without also having to worry about error priority if more than one error occurs. Even though error_propagate() can be safely used to ignore a second error during cleanup caused by a first error, it is simpler if the cleanup cannot set an error. So, split out the error checking portion (basically, input visitors checking for unvisited keys) into a new function visit_check_struct(), which can be safely skipped if any earlier errors are encountered, and leave the cleanup portion (which never fails, but must be called unconditionally if visit_start_struct() succeeded) in visit_end_struct(). Generated code in qapi-visit.c has diffs resembling: |@@ -59,10 +59,12 @@ void visit_type_ACPIOSTInfo(Visitor *v, | goto out_obj; | } | visit_type_ACPIOSTInfo_members(v, obj, &err); |- error_propagate(errp, err); |- err = NULL; |+ if (err) { |+ goto out_obj; |+ } |+ visit_check_struct(v, &err); | out_obj: |- visit_end_struct(v, &err); |+ visit_end_struct(v); | out: and in qapi-event.c: @@ -47,7 +47,10 @@ void qapi_event_send_acpi_device_ost(ACP | goto out; | } | visit_type_q_obj_ACPI_DEVICE_OST_arg_members(v, &param, &err); |- visit_end_struct(v, err ? NULL : &err); |+ if (!err) { |+ visit_check_struct(v, &err); |+ } |+ visit_end_struct(v); | if (err) { | goto out; Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <1461879932-9020-20-git-send-email-eblake@redhat.com> [Conflict with a doc fixup resolved] Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-04-29 00:45:27 +03:00
visit_check_struct(v, &err);
2016-06-09 19:48:34 +03:00
visit_end_struct(v, NULL);
if (err) {
error_propagate(errp, err);
return;
}
fdt_depth--;
break;
case FDT_PROP: {
int i;
prop = fdt_get_property_by_offset(fdt, fdt_offset, &prop_len);
name = fdt_string(fdt, fdt32_to_cpu(prop->nameoff));
qapi: Simplify semantics of visit_next_list() The semantics of the list visit are somewhat baroque, with the following pseudocode when FooList is used: start() for (prev = head; cur = next(prev); prev = &cur) { visit(&cur->value) } Note that these semantics (advance before visit) requires that the first call to next() return the list head, while all other calls return the next element of the list; that is, every visitor implementation is required to track extra state to decide whether to return the input as-is, or to advance. It also requires an argument of 'GenericList **' to next(), solely because the first iteration might need to modify the caller's GenericList head, so that all other calls have to do a layer of dereferencing. Thankfully, we only have two uses of list visits in the entire code base: one in spapr_drc (which completely avoids visit_next_list(), feeding in integers from a different source than uint8List), and one in qapi-visit.py. That is, all other list visitors are generated in qapi-visit.c, and share the same paradigm based on a qapi FooList type, so we can refactor how lists are laid out with minimal churn among clients. We can greatly simplify things by hoisting the special case into the start() routine, and flipping the order in the loop to visit before advance: start(head) for (tail = *head; tail; tail = next(tail)) { visit(&tail->value) } With the simpler semantics, visitors have less state to track, the argument to next() is reduced to 'GenericList *', and it also becomes obvious whether an input visitor is allocating a FooList during visit_start_list() (rather than the old way of not knowing if an allocation happened until the first visit_next_list()). As a minor drawback, we now allocate in two functions instead of one, and have to pass the size to both functions (unless we were to tweak the input visitors to cache the size to start_list for reuse during next_list, but that defeats the goal of less visitor state). The signature of visit_start_list() is chosen to match visit_start_struct(), with the new parameters after 'name'. The spapr_drc case is a virtual visit, done by passing NULL for list, similarly to how NULL is passed to visit_start_struct() when a qapi type is not used in those visits. It was easy to provide these semantics for qmp-output and dealloc visitors, and a bit harder for qmp-input (several prerequisite patches refactored things to make this patch straightforward). But it turned out that the string and opts visitors munge enough other state during visit_next_list() to make it easier to just document and require a GenericList visit for now; an assertion will remind us to adjust things if we need the semantics in the future. Several pre-requisite cleanup patches made the reshuffling of the various visitors easier; particularly the qmp input visitor. Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <1461879932-9020-24-git-send-email-eblake@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-04-29 00:45:31 +03:00
visit_start_list(v, name, NULL, 0, &err);
if (err) {
error_propagate(errp, err);
return;
}
for (i = 0; i < prop_len; i++) {
qapi: Swap visit_* arguments for consistent 'name' placement JSON uses "name":value, but many of our visitor interfaces were called with visit_type_FOO(v, &value, name, errp). This can be a bit confusing to have to mentally swap the parameter order to match JSON order. It's particularly bad for visit_start_struct(), where the 'name' parameter is smack in the middle of the otherwise-related group of 'obj, kind, size' parameters! It's time to do a global swap of the parameter ordering, so that the 'name' parameter is always immediately after the Visitor argument. Additional reason in favor of the swap: the existing include/qjson.h prefers listing 'name' first in json_prop_*(), and I have plans to unify that file with the qapi visitors; listing 'name' first in qapi will minimize churn to the (admittedly few) qjson.h clients. Later patches will then fix docs, object.h, visitor-impl.h, and those clients to match. Done by first patching scripts/qapi*.py by hand to make generated files do what I want, then by running the following Coccinelle script to affect the rest of the code base: $ spatch --sp-file script `git grep -l '\bvisit_' -- '**/*.[ch]'` I then had to apply some touchups (Coccinelle insisted on TAB indentation in visitor.h, and botched the signature of visit_type_enum() by rewriting 'const char *const strings[]' to the syntactically invalid 'const char*const[] strings'). The movement of parameters is sufficient to provoke compiler errors if any callers were missed. // Part 1: Swap declaration order @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_start_struct -(TV v, TObj OBJ, T1 ARG1, const char *name, T2 ARG2, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type bool, TV, T1; identifier ARG1; @@ bool visit_optional -(TV v, T1 ARG1, const char *name) +(TV v, const char *name, T1 ARG1) { ... } @@ type TV, TErr, TObj, T1; identifier OBJ, ARG1; @@ void visit_get_next_type -(TV v, TObj OBJ, T1 ARG1, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, TErr errp) { ... } @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_type_enum -(TV v, TObj OBJ, T1 ARG1, T2 ARG2, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type TV, TErr, TObj; identifier OBJ; identifier VISIT_TYPE =~ "^visit_type_"; @@ void VISIT_TYPE -(TV v, TObj OBJ, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, TErr errp) { ... } // Part 2: swap caller order @@ expression V, NAME, OBJ, ARG1, ARG2, ERR; identifier VISIT_TYPE =~ "^visit_type_"; @@ ( -visit_start_struct(V, OBJ, ARG1, NAME, ARG2, ERR) +visit_start_struct(V, NAME, OBJ, ARG1, ARG2, ERR) | -visit_optional(V, ARG1, NAME) +visit_optional(V, NAME, ARG1) | -visit_get_next_type(V, OBJ, ARG1, NAME, ERR) +visit_get_next_type(V, NAME, OBJ, ARG1, ERR) | -visit_type_enum(V, OBJ, ARG1, ARG2, NAME, ERR) +visit_type_enum(V, NAME, OBJ, ARG1, ARG2, ERR) | -VISIT_TYPE(V, OBJ, NAME, ERR) +VISIT_TYPE(V, NAME, OBJ, ERR) ) Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-Id: <1454075341-13658-19-git-send-email-eblake@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-01-29 16:48:54 +03:00
visit_type_uint8(v, NULL, (uint8_t *)&prop->data[i], &err);
if (err) {
error_propagate(errp, err);
return;
}
}
visit_check_list(v, &err);
2016-06-09 19:48:34 +03:00
visit_end_list(v, NULL);
if (err) {
error_propagate(errp, err);
return;
}
break;
}
default:
error_report("device FDT in unexpected state: %d", tag);
abort();
}
fdt_offset = fdt_offset_next;
} while (fdt_depth != 0);
}
void spapr_drc_attach(sPAPRDRConnector *drc, DeviceState *d, Error **errp)
{
trace_spapr_drc_attach(spapr_drc_index(drc));
if (drc->dev) {
error_setg(errp, "an attached device is still awaiting release");
return;
}
g_assert((drc->state == SPAPR_DRC_STATE_LOGICAL_UNUSABLE)
|| (drc->state == SPAPR_DRC_STATE_PHYSICAL_POWERON));
drc->dev = d;
spapr_drc: Allow FDT fragment to be added later The current logic is to provide the FDT fragment when attaching a device to a DRC. This works perfectly fine for our current hotplug support, but soon we will add support for PHB hotplug which has some constraints, that CPU, PCI and LMB devices don't seem to have. The first constraint is that the "ibm,dma-window" property of the PHB node requires the IOMMU to be configured, ie, spapr_tce_table_enable() has been called, which happens during PHB reset. It is okay in the case of hotplug since the device is reset before the hotplug handler is called. On the contrary with coldplug, the hotplug handler is called first and device is only reset during the initial system reset. Trying to create the FDT fragment on the hotplug path in this case, would result in somthing like this: ibm,dma-window = < 0x80000000 0x00 0x00 0x00 0x00 >; This will cause linux in the guest to panic, by simply removing and re-adding the PHB using the drmgr command: page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz)); if (!page) panic("iommu_init_table: Can't allocate %ld bytes\n", sz); The second and maybe more problematic constraint is that the "interrupt-map" property needs to reference the interrupt controller node using the very same phandle that SLOF has already exposed to the guest. QEMU requires SLOF to call the private KVMPPC_H_UPDATE_DT hcall at some point to know about this phandle. With the latest QEMU and SLOF, this happens when SLOF gets quiesced. This means that if the PHB gets hotplugged after CAS but before SLOF quiesce, then we're sure that the phandle is not known when the hotplug handler is called. The FDT is only needed when the guest first invokes RTAS to configure the connector actually, long after SLOF quiesce. Let's postpone the creation of FDT fragments for PHBs to rtas_ibm_configure_connector(). Since we only need this for PHBs, introduce a new method in the base DRC class for that. DRC subtypes will be converted to use it in subsequent patches. Allow spapr_drc_attach() to be passed a NULL fdt argument if the method is available. When all DRC subtypes have been converted, the fdt argument will eventually disappear. Signed-off-by: Greg Kurz <groug@kaod.org> Message-Id: <155059665823.1466090.18358845122627355537.stgit@bahia.lab.toulouse-stg.fr.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-02-19 20:17:38 +03:00
object_property_add_link(OBJECT(drc), "device",
object_get_typename(OBJECT(drc->dev)),
(Object **)(&drc->dev),
NULL, 0, NULL);
}
static void spapr_drc_release(sPAPRDRConnector *drc)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
drck->release(drc->dev);
drc->unplug_requested = false;
g_free(drc->fdt);
drc->fdt = NULL;
drc->fdt_start_offset = 0;
object_property_del(OBJECT(drc), "device", &error_abort);
drc->dev = NULL;
}
void spapr_drc_detach(sPAPRDRConnector *drc)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
trace_spapr_drc_detach(spapr_drc_index(drc));
g_assert(drc->dev);
drc->unplug_requested = true;
if (drc->state != drck->empty_state) {
trace_spapr_drc_awaiting_quiesce(spapr_drc_index(drc));
return;
}
spapr_drc_release(drc);
}
spapr: Treat devices added before inbound migration as coldplugged When migrating a guest which has already had devices hotplugged, libvirt typically starts the destination qemu with -incoming defer, adds those hotplugged devices with qmp, then initiates the incoming migration. This causes problems for the management of spapr DRC state. Because the device is treated as hotplugged, it goes into a DRC state for a device immediately after it's plugged, but before the guest has acknowledged its presence. However, chances are the guest on the source machine *has* acknowledged the device's presence and configured it. If the source has fully configured the device, then DRC state won't be sent in the migration stream: for maximum migration compatibility with earlier versions we don't migrate DRCs in coldplug-equivalent state. That means that the DRC effectively changes state over the migrate, causing problems later on. In addition, logging hotplug events for these devices isn't what we want because a) those events should already have been issued on the source host and b) the event queue should get wiped out by the incoming state anyway. In short, what we really want is to treat devices added before an incoming migration as if they were coldplugged. To do this, we first add a spapr_drc_hotplugged() helper which determines if the device is hotplugged in the sense relevant for DRC state management. We only send hotplug events when this is true. Second, when we add a device which isn't hotplugged in this sense, we force a reset of the DRC state - this ensures the DRC is in a coldplug-equivalent state (there isn't usually a system reset between these device adds and the incoming migration). This is based on an earlier patch by Laurent Vivier, cleaned up and extended. Signed-off-by: Laurent Vivier <lvivier@redhat.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Greg Kurz <groug@kaod.org> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-09 14:08:10 +03:00
void spapr_drc_reset(sPAPRDRConnector *drc)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
trace_spapr_drc_reset(spapr_drc_index(drc));
/* immediately upon reset we can safely assume DRCs whose devices
* are pending removal can be safely removed.
*/
if (drc->unplug_requested) {
spapr_drc_release(drc);
}
if (drc->dev) {
/* A device present at reset is ready to go, same as coldplugged */
drc->state = drck->ready_state;
/*
* Ensure that we are able to send the FDT fragment again
* via configure-connector call if the guest requests.
*/
drc->ccs_offset = drc->fdt_start_offset;
drc->ccs_depth = 0;
} else {
drc->state = drck->empty_state;
drc->ccs_offset = -1;
drc->ccs_depth = -1;
}
}
hw/ppc: CAS reset on early device hotplug This patch is a follow up on the discussions made in patch "hw/ppc: disable hotplug before CAS is completed" that can be found at [1]. At this moment, we do not support CPU/memory hotplug in early boot stages, before CAS. When a hotplug occurs, the event is logged in an internal RTAS event log queue and an IRQ pulse is fired. In regular conditions, the guest handles the interrupt by executing check_exception, fetching the generated hotplug event and enabling the device for use. In early boot, this IRQ isn't caught (SLOF does not handle hotplug events), leaving the event in the rtas event log queue. If the guest executes check_exception due to another hotplug event, the re-assertion of the IRQ ends up de-queuing the first hotplug event as well. In short, a device hotplugged before CAS is considered coldplugged by SLOF. This leads to device misbehavior and, in some cases, guest kernel Ooops when trying to unplug the device. A proper fix would be to turn every device hotplugged before CAS as a colplugged device. This is not trivial to do with the current code base though - the FDT is written in the guest memory at ppc_spapr_reset and can't be retrieved without adding extra state (fdt_size for example) that will need to managed and migrated. Adding the hotplugged DT in the middle of CAS negotiation via the updated DT tree works with CPU devs, but panics the guest kernel at boot. Additional analysis would be necessary for LMBs and PCI devices. There are questions to be made in QEMU/SLOF/kernel level about how we can make this change in a sustainable way. With Linux guests, a fix would be the kernel executing check_exception at boot time, de-queueing the events that happened in early boot and processing them. However, even if/when the newer kernels start fetching these events at boot time, we need to take care of older kernels that won't be doing that. This patch works around the situation by issuing a CAS reset if a hotplugged device is detected during CAS: - the DRC conditions that warrant a CAS reset is the same as those that triggers a DRC migration - the DRC must have a device attached and the DRC state is not equal to its ready_state. With that in mind, this patch makes use of 'spapr_drc_needed' to determine if a CAS reset is needed. - In the middle of CAS negotiations, the function 'spapr_hotplugged_dev_before_cas' goes through all the DRCs to see if there are any DRC that requires a reset, using spapr_drc_needed. If that happens, returns '1' in 'spapr_h_cas_compose_response' which will set spapr->cas_reboot to true, causing the machine to reboot. No changes are made for coldplug devices. [1] http://lists.nongnu.org/archive/html/qemu-devel/2017-08/msg02855.html Signed-off-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2017-08-30 21:21:41 +03:00
bool spapr_drc_needed(void *opaque)
hw/ppc: migrating the DRC state of hotplugged devices In pseries, a firmware abstraction called Dynamic Reconfiguration Connector (DRC) is used to assign a particular dynamic resource to the guest and provide an interface to manage configuration/removal of the resource associated with it. In other words, DRC is the 'plugged state' of a device. Before this patch, DRC wasn't being migrated. This causes post-migration problems due to DRC state mismatch between source and target. The DRC state of a device X in the source might change, while in the target the DRC state of X is still fresh. When migrating the guest, X will not have the same hotplugged state as it did in the source. This means that we can't hot unplug X in the target after migration is completed because its DRC state is not consistent. https://bugs.launchpad.net/ubuntu/+source/qemu/+bug/1677552 is one bug that is caused by this DRC state mismatch between source and target. To migrate the DRC state, we defined the VMStateDescription struct for spapr_drc to enable the transmission of spapr_drc state in migration. Not all the elements in the DRC state are migrated - only those that can be modified by guest actions or device add/remove operations: - 'isolation_state', 'allocation_state' and 'indicator_state' are involved in the DR state transition diagram from PAPR+ 2.7, 13.4; - 'configured', 'signalled', 'awaiting_release' and 'awaiting_allocation' are needed in attaching and detaching devices; - 'indicator_state' provides users with hardware state information. These are the DRC elements that are migrated. In this patch the DRC state is migrated for PCI, LMB and CPU connector types. At this moment there is no support to migrate DRC for the PHB (PCI Host Bridge) type. In the 'realize' function the DRC is registered using vmstate_register, similar to what hw/ppc/spapr_iommu.c does in 'spapr_tce_table_realize'. This approach works because DRCs are bus-less and do not sit on a BusClass that implements bc->get_dev_path, so as a fallback the VMSD gets identified via "spapr_drc"/get_index(drc). Signed-off-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2017-05-22 22:35:49 +03:00
{
sPAPRDRConnector *drc = (sPAPRDRConnector *)opaque;
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
/* If no dev is plugged in there is no need to migrate the DRC state */
if (!drc->dev) {
hw/ppc: migrating the DRC state of hotplugged devices In pseries, a firmware abstraction called Dynamic Reconfiguration Connector (DRC) is used to assign a particular dynamic resource to the guest and provide an interface to manage configuration/removal of the resource associated with it. In other words, DRC is the 'plugged state' of a device. Before this patch, DRC wasn't being migrated. This causes post-migration problems due to DRC state mismatch between source and target. The DRC state of a device X in the source might change, while in the target the DRC state of X is still fresh. When migrating the guest, X will not have the same hotplugged state as it did in the source. This means that we can't hot unplug X in the target after migration is completed because its DRC state is not consistent. https://bugs.launchpad.net/ubuntu/+source/qemu/+bug/1677552 is one bug that is caused by this DRC state mismatch between source and target. To migrate the DRC state, we defined the VMStateDescription struct for spapr_drc to enable the transmission of spapr_drc state in migration. Not all the elements in the DRC state are migrated - only those that can be modified by guest actions or device add/remove operations: - 'isolation_state', 'allocation_state' and 'indicator_state' are involved in the DR state transition diagram from PAPR+ 2.7, 13.4; - 'configured', 'signalled', 'awaiting_release' and 'awaiting_allocation' are needed in attaching and detaching devices; - 'indicator_state' provides users with hardware state information. These are the DRC elements that are migrated. In this patch the DRC state is migrated for PCI, LMB and CPU connector types. At this moment there is no support to migrate DRC for the PHB (PCI Host Bridge) type. In the 'realize' function the DRC is registered using vmstate_register, similar to what hw/ppc/spapr_iommu.c does in 'spapr_tce_table_realize'. This approach works because DRCs are bus-less and do not sit on a BusClass that implements bc->get_dev_path, so as a fallback the VMSD gets identified via "spapr_drc"/get_index(drc). Signed-off-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2017-05-22 22:35:49 +03:00
return false;
}
/*
* We need to migrate the state if it's not equal to the expected
* long-term state, which is the same as the coldplugged initial
* state */
return (drc->state != drck->ready_state);
hw/ppc: migrating the DRC state of hotplugged devices In pseries, a firmware abstraction called Dynamic Reconfiguration Connector (DRC) is used to assign a particular dynamic resource to the guest and provide an interface to manage configuration/removal of the resource associated with it. In other words, DRC is the 'plugged state' of a device. Before this patch, DRC wasn't being migrated. This causes post-migration problems due to DRC state mismatch between source and target. The DRC state of a device X in the source might change, while in the target the DRC state of X is still fresh. When migrating the guest, X will not have the same hotplugged state as it did in the source. This means that we can't hot unplug X in the target after migration is completed because its DRC state is not consistent. https://bugs.launchpad.net/ubuntu/+source/qemu/+bug/1677552 is one bug that is caused by this DRC state mismatch between source and target. To migrate the DRC state, we defined the VMStateDescription struct for spapr_drc to enable the transmission of spapr_drc state in migration. Not all the elements in the DRC state are migrated - only those that can be modified by guest actions or device add/remove operations: - 'isolation_state', 'allocation_state' and 'indicator_state' are involved in the DR state transition diagram from PAPR+ 2.7, 13.4; - 'configured', 'signalled', 'awaiting_release' and 'awaiting_allocation' are needed in attaching and detaching devices; - 'indicator_state' provides users with hardware state information. These are the DRC elements that are migrated. In this patch the DRC state is migrated for PCI, LMB and CPU connector types. At this moment there is no support to migrate DRC for the PHB (PCI Host Bridge) type. In the 'realize' function the DRC is registered using vmstate_register, similar to what hw/ppc/spapr_iommu.c does in 'spapr_tce_table_realize'. This approach works because DRCs are bus-less and do not sit on a BusClass that implements bc->get_dev_path, so as a fallback the VMSD gets identified via "spapr_drc"/get_index(drc). Signed-off-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2017-05-22 22:35:49 +03:00
}
static const VMStateDescription vmstate_spapr_drc = {
.name = "spapr_drc",
.version_id = 1,
.minimum_version_id = 1,
.needed = spapr_drc_needed,
.fields = (VMStateField []) {
VMSTATE_UINT32(state, sPAPRDRConnector),
hw/ppc: migrating the DRC state of hotplugged devices In pseries, a firmware abstraction called Dynamic Reconfiguration Connector (DRC) is used to assign a particular dynamic resource to the guest and provide an interface to manage configuration/removal of the resource associated with it. In other words, DRC is the 'plugged state' of a device. Before this patch, DRC wasn't being migrated. This causes post-migration problems due to DRC state mismatch between source and target. The DRC state of a device X in the source might change, while in the target the DRC state of X is still fresh. When migrating the guest, X will not have the same hotplugged state as it did in the source. This means that we can't hot unplug X in the target after migration is completed because its DRC state is not consistent. https://bugs.launchpad.net/ubuntu/+source/qemu/+bug/1677552 is one bug that is caused by this DRC state mismatch between source and target. To migrate the DRC state, we defined the VMStateDescription struct for spapr_drc to enable the transmission of spapr_drc state in migration. Not all the elements in the DRC state are migrated - only those that can be modified by guest actions or device add/remove operations: - 'isolation_state', 'allocation_state' and 'indicator_state' are involved in the DR state transition diagram from PAPR+ 2.7, 13.4; - 'configured', 'signalled', 'awaiting_release' and 'awaiting_allocation' are needed in attaching and detaching devices; - 'indicator_state' provides users with hardware state information. These are the DRC elements that are migrated. In this patch the DRC state is migrated for PCI, LMB and CPU connector types. At this moment there is no support to migrate DRC for the PHB (PCI Host Bridge) type. In the 'realize' function the DRC is registered using vmstate_register, similar to what hw/ppc/spapr_iommu.c does in 'spapr_tce_table_realize'. This approach works because DRCs are bus-less and do not sit on a BusClass that implements bc->get_dev_path, so as a fallback the VMSD gets identified via "spapr_drc"/get_index(drc). Signed-off-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2017-05-22 22:35:49 +03:00
VMSTATE_END_OF_LIST()
}
};
static void realize(DeviceState *d, Error **errp)
{
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(d);
Object *root_container;
gchar *link_name;
gchar *child_name;
Error *err = NULL;
trace_spapr_drc_realize(spapr_drc_index(drc));
/* NOTE: we do this as part of realize/unrealize due to the fact
* that the guest will communicate with the DRC via RTAS calls
* referencing the global DRC index. By unlinking the DRC
* from DRC_CONTAINER_PATH/<drc_index> we effectively make it
* inaccessible by the guest, since lookups rely on this path
* existing in the composition tree
*/
root_container = container_get(object_get_root(), DRC_CONTAINER_PATH);
link_name = g_strdup_printf("%x", spapr_drc_index(drc));
child_name = object_get_canonical_path_component(OBJECT(drc));
trace_spapr_drc_realize_child(spapr_drc_index(drc), child_name);
object_property_add_alias(root_container, link_name,
drc->owner, child_name, &err);
g_free(child_name);
g_free(link_name);
if (err) {
error_propagate(errp, err);
return;
}
vmstate_register(DEVICE(drc), spapr_drc_index(drc), &vmstate_spapr_drc,
hw/ppc: migrating the DRC state of hotplugged devices In pseries, a firmware abstraction called Dynamic Reconfiguration Connector (DRC) is used to assign a particular dynamic resource to the guest and provide an interface to manage configuration/removal of the resource associated with it. In other words, DRC is the 'plugged state' of a device. Before this patch, DRC wasn't being migrated. This causes post-migration problems due to DRC state mismatch between source and target. The DRC state of a device X in the source might change, while in the target the DRC state of X is still fresh. When migrating the guest, X will not have the same hotplugged state as it did in the source. This means that we can't hot unplug X in the target after migration is completed because its DRC state is not consistent. https://bugs.launchpad.net/ubuntu/+source/qemu/+bug/1677552 is one bug that is caused by this DRC state mismatch between source and target. To migrate the DRC state, we defined the VMStateDescription struct for spapr_drc to enable the transmission of spapr_drc state in migration. Not all the elements in the DRC state are migrated - only those that can be modified by guest actions or device add/remove operations: - 'isolation_state', 'allocation_state' and 'indicator_state' are involved in the DR state transition diagram from PAPR+ 2.7, 13.4; - 'configured', 'signalled', 'awaiting_release' and 'awaiting_allocation' are needed in attaching and detaching devices; - 'indicator_state' provides users with hardware state information. These are the DRC elements that are migrated. In this patch the DRC state is migrated for PCI, LMB and CPU connector types. At this moment there is no support to migrate DRC for the PHB (PCI Host Bridge) type. In the 'realize' function the DRC is registered using vmstate_register, similar to what hw/ppc/spapr_iommu.c does in 'spapr_tce_table_realize'. This approach works because DRCs are bus-less and do not sit on a BusClass that implements bc->get_dev_path, so as a fallback the VMSD gets identified via "spapr_drc"/get_index(drc). Signed-off-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2017-05-22 22:35:49 +03:00
drc);
trace_spapr_drc_realize_complete(spapr_drc_index(drc));
}
static void unrealize(DeviceState *d, Error **errp)
{
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(d);
Object *root_container;
gchar *name;
trace_spapr_drc_unrealize(spapr_drc_index(drc));
vmstate_unregister(DEVICE(drc), &vmstate_spapr_drc, drc);
root_container = container_get(object_get_root(), DRC_CONTAINER_PATH);
name = g_strdup_printf("%x", spapr_drc_index(drc));
object_property_del(root_container, name, errp);
g_free(name);
}
sPAPRDRConnector *spapr_dr_connector_new(Object *owner, const char *type,
uint32_t id)
{
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(object_new(type));
spapr: Don't use QOM [*] syntax for DR connectors. The dynamic reconfiguration (hotplug) code for the pseries machine type uses a "DR connector" QOM object for each resource it will be possible to hotplug. Each of these is added to its owner using object_property_add_child(owner, "dr-connector[*], ...); That works ok, mostly, but it means that the property indices are arbitrary, depending on the order in which the connectors are constructed. That might line up to something useful, but it doesn't have to. It will get worse once we add hotplug RAM support. That will add a DR connector object for every 256MB of potential memory. So if maxmem=2T, for example, there are 8192 objects under the same parent. The QOM interfaces aren't really designed for this. In particular object_property_add() with [*] has O(n^2) time complexity (in the number of existing children): first it has a linear search through array indices to find a free slot, each of which is attempted to a recursive call to object_property_add() with a specific [N]. Those calls are O(n) because there's a linear search through all properties to check for duplicates. By using a meaningful index value, which we already know is unique we can avoid the [*] special behaviour. That lets us reduce the total time for creating the DR objects from O(n^3) to O(n^2). O(n^2) is still kind of crappy, but it's enough to reduce the startup time of qemu (with in-progress memory hotplug support) with maxmem=2T from ~20 minutes to ~4 seconds. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Bharata B Rao <bharata@linux.vnet.ibm.com> Tested-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
2015-09-16 09:57:51 +03:00
char *prop_name;
drc->id = id;
drc->owner = owner;
prop_name = g_strdup_printf("dr-connector[%"PRIu32"]",
spapr_drc_index(drc));
object_property_add_child(owner, prop_name, OBJECT(drc), &error_abort);
object_unref(OBJECT(drc));
object_property_set_bool(OBJECT(drc), true, "realized", NULL);
spapr: Don't use QOM [*] syntax for DR connectors. The dynamic reconfiguration (hotplug) code for the pseries machine type uses a "DR connector" QOM object for each resource it will be possible to hotplug. Each of these is added to its owner using object_property_add_child(owner, "dr-connector[*], ...); That works ok, mostly, but it means that the property indices are arbitrary, depending on the order in which the connectors are constructed. That might line up to something useful, but it doesn't have to. It will get worse once we add hotplug RAM support. That will add a DR connector object for every 256MB of potential memory. So if maxmem=2T, for example, there are 8192 objects under the same parent. The QOM interfaces aren't really designed for this. In particular object_property_add() with [*] has O(n^2) time complexity (in the number of existing children): first it has a linear search through array indices to find a free slot, each of which is attempted to a recursive call to object_property_add() with a specific [N]. Those calls are O(n) because there's a linear search through all properties to check for duplicates. By using a meaningful index value, which we already know is unique we can avoid the [*] special behaviour. That lets us reduce the total time for creating the DR objects from O(n^3) to O(n^2). O(n^2) is still kind of crappy, but it's enough to reduce the startup time of qemu (with in-progress memory hotplug support) with maxmem=2T from ~20 minutes to ~4 seconds. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Bharata B Rao <bharata@linux.vnet.ibm.com> Tested-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
2015-09-16 09:57:51 +03:00
g_free(prop_name);
return drc;
}
static void spapr_dr_connector_instance_init(Object *obj)
{
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj);
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
object_property_add_uint32_ptr(obj, "id", &drc->id, NULL);
object_property_add(obj, "index", "uint32", prop_get_index,
NULL, NULL, NULL, NULL);
object_property_add(obj, "fdt", "struct", prop_get_fdt,
NULL, NULL, NULL, NULL);
drc->state = drck->empty_state;
}
static void spapr_dr_connector_class_init(ObjectClass *k, void *data)
{
DeviceClass *dk = DEVICE_CLASS(k);
dk->realize = realize;
dk->unrealize = unrealize;
/*
* Reason: it crashes FIXME find and document the real reason
*/
qdev: Replace cannot_instantiate_with_device_add_yet with !user_creatable cannot_instantiate_with_device_add_yet was introduced by commit efec3dd631d94160288392721a5f9c39e50fb2bc to replace no_user. It was supposed to be a temporary measure. When it was introduced, we had 54 cannot_instantiate_with_device_add_yet=true lines in the code. Today (3 years later) this number has not shrunk: we now have 57 cannot_instantiate_with_device_add_yet=true lines. I think it is safe to say it is not a temporary measure, and we won't see the flag go away soon. Instead of a long field name that misleads people to believe it is temporary, replace it a shorter and less misleading field: user_creatable. Except for code comments, changes were generated using the following Coccinelle patch: @@ expression DC; @@ ( -DC->cannot_instantiate_with_device_add_yet = false; +DC->user_creatable = true; | -DC->cannot_instantiate_with_device_add_yet = true; +DC->user_creatable = false; ) @@ typedef ObjectClass; expression dc; identifier class, data; @@ static void device_class_init(ObjectClass *class, void *data) { ... dc->hotpluggable = true; +dc->user_creatable = true; ... } @@ @@ struct DeviceClass { ... -bool cannot_instantiate_with_device_add_yet; +bool user_creatable; ... } @@ expression DC; @@ ( -!DC->cannot_instantiate_with_device_add_yet +DC->user_creatable | -DC->cannot_instantiate_with_device_add_yet +!DC->user_creatable ) Cc: Alistair Francis <alistair.francis@xilinx.com> Cc: Laszlo Ersek <lersek@redhat.com> Cc: Marcel Apfelbaum <marcel@redhat.com> Cc: Markus Armbruster <armbru@redhat.com> Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Thomas Huth <thuth@redhat.com> Acked-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Marcel Apfelbaum <marcel@redhat.com> Acked-by: Marcel Apfelbaum <marcel@redhat.com> Signed-off-by: Eduardo Habkost <ehabkost@redhat.com> Message-Id: <20170503203604.31462-2-ehabkost@redhat.com> [ehabkost: kept "TODO remove once we're there" comment] Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
2017-05-03 23:35:44 +03:00
dk->user_creatable = false;
}
static bool drc_physical_needed(void *opaque)
{
sPAPRDRCPhysical *drcp = (sPAPRDRCPhysical *)opaque;
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(drcp);
if ((drc->dev && (drcp->dr_indicator == SPAPR_DR_INDICATOR_ACTIVE))
|| (!drc->dev && (drcp->dr_indicator == SPAPR_DR_INDICATOR_INACTIVE))) {
return false;
}
return true;
}
static const VMStateDescription vmstate_spapr_drc_physical = {
.name = "spapr_drc/physical",
.version_id = 1,
.minimum_version_id = 1,
.needed = drc_physical_needed,
.fields = (VMStateField []) {
VMSTATE_UINT32(dr_indicator, sPAPRDRCPhysical),
VMSTATE_END_OF_LIST()
}
};
static void drc_physical_reset(void *opaque)
{
sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(opaque);
sPAPRDRCPhysical *drcp = SPAPR_DRC_PHYSICAL(drc);
if (drc->dev) {
drcp->dr_indicator = SPAPR_DR_INDICATOR_ACTIVE;
} else {
drcp->dr_indicator = SPAPR_DR_INDICATOR_INACTIVE;
}
}
static void realize_physical(DeviceState *d, Error **errp)
{
sPAPRDRCPhysical *drcp = SPAPR_DRC_PHYSICAL(d);
Error *local_err = NULL;
realize(d, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
vmstate_register(DEVICE(drcp), spapr_drc_index(SPAPR_DR_CONNECTOR(drcp)),
&vmstate_spapr_drc_physical, drcp);
qemu_register_reset(drc_physical_reset, drcp);
}
static void unrealize_physical(DeviceState *d, Error **errp)
{
sPAPRDRCPhysical *drcp = SPAPR_DRC_PHYSICAL(d);
Error *local_err = NULL;
unrealize(d, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
vmstate_unregister(DEVICE(drcp), &vmstate_spapr_drc_physical, drcp);
qemu_unregister_reset(drc_physical_reset, drcp);
}
static void spapr_drc_physical_class_init(ObjectClass *k, void *data)
{
DeviceClass *dk = DEVICE_CLASS(k);
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k);
dk->realize = realize_physical;
dk->unrealize = unrealize_physical;
drck->dr_entity_sense = physical_entity_sense;
drck->isolate = drc_isolate_physical;
drck->unisolate = drc_unisolate_physical;
drck->ready_state = SPAPR_DRC_STATE_PHYSICAL_CONFIGURED;
drck->empty_state = SPAPR_DRC_STATE_PHYSICAL_POWERON;
}
static void spapr_drc_logical_class_init(ObjectClass *k, void *data)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k);
drck->dr_entity_sense = logical_entity_sense;
drck->isolate = drc_isolate_logical;
drck->unisolate = drc_unisolate_logical;
drck->ready_state = SPAPR_DRC_STATE_LOGICAL_CONFIGURED;
drck->empty_state = SPAPR_DRC_STATE_LOGICAL_UNUSABLE;
}
static void spapr_drc_cpu_class_init(ObjectClass *k, void *data)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k);
drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_CPU;
drck->typename = "CPU";
drck->drc_name_prefix = "CPU ";
drck->release = spapr_core_release;
drck->dt_populate = spapr_core_dt_populate;
}
static void spapr_drc_pci_class_init(ObjectClass *k, void *data)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k);
drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_PCI;
drck->typename = "28";
drck->drc_name_prefix = "C";
drck->release = spapr_phb_remove_pci_device_cb;
drck->dt_populate = spapr_pci_dt_populate;
}
static void spapr_drc_lmb_class_init(ObjectClass *k, void *data)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k);
drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_LMB;
drck->typename = "MEM";
drck->drc_name_prefix = "LMB ";
drck->release = spapr_lmb_release;
drck->dt_populate = spapr_lmb_dt_populate;
}
static void spapr_drc_phb_class_init(ObjectClass *k, void *data)
{
sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k);
drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_PHB;
drck->typename = "PHB";
drck->drc_name_prefix = "PHB ";
drck->release = spapr_phb_release;
drck->dt_populate = spapr_phb_dt_populate;
}
static const TypeInfo spapr_dr_connector_info = {
.name = TYPE_SPAPR_DR_CONNECTOR,
.parent = TYPE_DEVICE,
.instance_size = sizeof(sPAPRDRConnector),
.instance_init = spapr_dr_connector_instance_init,
.class_size = sizeof(sPAPRDRConnectorClass),
.class_init = spapr_dr_connector_class_init,
.abstract = true,
};
static const TypeInfo spapr_drc_physical_info = {
.name = TYPE_SPAPR_DRC_PHYSICAL,
.parent = TYPE_SPAPR_DR_CONNECTOR,
.instance_size = sizeof(sPAPRDRCPhysical),
.class_init = spapr_drc_physical_class_init,
.abstract = true,
};
static const TypeInfo spapr_drc_logical_info = {
.name = TYPE_SPAPR_DRC_LOGICAL,
.parent = TYPE_SPAPR_DR_CONNECTOR,
.class_init = spapr_drc_logical_class_init,
.abstract = true,
};
static const TypeInfo spapr_drc_cpu_info = {
.name = TYPE_SPAPR_DRC_CPU,
.parent = TYPE_SPAPR_DRC_LOGICAL,
.class_init = spapr_drc_cpu_class_init,
};
static const TypeInfo spapr_drc_pci_info = {
.name = TYPE_SPAPR_DRC_PCI,
.parent = TYPE_SPAPR_DRC_PHYSICAL,
.class_init = spapr_drc_pci_class_init,
};
static const TypeInfo spapr_drc_lmb_info = {
.name = TYPE_SPAPR_DRC_LMB,
.parent = TYPE_SPAPR_DRC_LOGICAL,
.class_init = spapr_drc_lmb_class_init,
};
static const TypeInfo spapr_drc_phb_info = {
.name = TYPE_SPAPR_DRC_PHB,
.parent = TYPE_SPAPR_DRC_LOGICAL,
.instance_size = sizeof(sPAPRDRConnector),
.class_init = spapr_drc_phb_class_init,
};
/* helper functions for external users */
sPAPRDRConnector *spapr_drc_by_index(uint32_t index)
{
Object *obj;
gchar *name;
name = g_strdup_printf("%s/%x", DRC_CONTAINER_PATH, index);
obj = object_resolve_path(name, NULL);
g_free(name);
return !obj ? NULL : SPAPR_DR_CONNECTOR(obj);
}
sPAPRDRConnector *spapr_drc_by_id(const char *type, uint32_t id)
{
sPAPRDRConnectorClass *drck
= SPAPR_DR_CONNECTOR_CLASS(object_class_by_name(type));
return spapr_drc_by_index(drck->typeshift << DRC_INDEX_TYPE_SHIFT
| (id & DRC_INDEX_ID_MASK));
}
/**
* spapr_drc_populate_dt
*
* @fdt: libfdt device tree
* @path: path in the DT to generate properties
* @owner: parent Object/DeviceState for which to generate DRC
* descriptions for
* @drc_type_mask: mask of sPAPRDRConnectorType values corresponding
* to the types of DRCs to generate entries for
*
* generate OF properties to describe DRC topology/indices to guests
*
* as documented in PAPR+ v2.1, 13.5.2
*/
int spapr_drc_populate_dt(void *fdt, int fdt_offset, Object *owner,
uint32_t drc_type_mask)
{
Object *root_container;
ObjectProperty *prop;
ObjectPropertyIterator iter;
uint32_t drc_count = 0;
GArray *drc_indexes, *drc_power_domains;
GString *drc_names, *drc_types;
int ret;
/* the first entry of each properties is a 32-bit integer encoding
* the number of elements in the array. we won't know this until
* we complete the iteration through all the matching DRCs, but
* reserve the space now and set the offsets accordingly so we
* can fill them in later.
*/
drc_indexes = g_array_new(false, true, sizeof(uint32_t));
drc_indexes = g_array_set_size(drc_indexes, 1);
drc_power_domains = g_array_new(false, true, sizeof(uint32_t));
drc_power_domains = g_array_set_size(drc_power_domains, 1);
drc_names = g_string_set_size(g_string_new(NULL), sizeof(uint32_t));
drc_types = g_string_set_size(g_string_new(NULL), sizeof(uint32_t));
/* aliases for all DRConnector objects will be rooted in QOM
* composition tree at DRC_CONTAINER_PATH
*/
root_container = container_get(object_get_root(), DRC_CONTAINER_PATH);
object_property_iter_init(&iter, root_container);
while ((prop = object_property_iter_next(&iter))) {
Object *obj;
sPAPRDRConnector *drc;
sPAPRDRConnectorClass *drck;
uint32_t drc_index, drc_power_domain;
if (!strstart(prop->type, "link<", NULL)) {
continue;
}
obj = object_property_get_link(root_container, prop->name, NULL);
drc = SPAPR_DR_CONNECTOR(obj);
drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
if (owner && (drc->owner != owner)) {
continue;
}
if ((spapr_drc_type(drc) & drc_type_mask) == 0) {
continue;
}
drc_count++;
/* ibm,drc-indexes */
drc_index = cpu_to_be32(spapr_drc_index(drc));
g_array_append_val(drc_indexes, drc_index);
/* ibm,drc-power-domains */
drc_power_domain = cpu_to_be32(-1);
g_array_append_val(drc_power_domains, drc_power_domain);
/* ibm,drc-names */
drc_names = g_string_append(drc_names, spapr_drc_name(drc));
drc_names = g_string_insert_len(drc_names, -1, "\0", 1);
/* ibm,drc-types */
drc_types = g_string_append(drc_types, drck->typename);
drc_types = g_string_insert_len(drc_types, -1, "\0", 1);
}
/* now write the drc count into the space we reserved at the
* beginning of the arrays previously
*/
*(uint32_t *)drc_indexes->data = cpu_to_be32(drc_count);
*(uint32_t *)drc_power_domains->data = cpu_to_be32(drc_count);
*(uint32_t *)drc_names->str = cpu_to_be32(drc_count);
*(uint32_t *)drc_types->str = cpu_to_be32(drc_count);
ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-indexes",
drc_indexes->data,
drc_indexes->len * sizeof(uint32_t));
if (ret) {
error_report("Couldn't create ibm,drc-indexes property");
goto out;
}
ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-power-domains",
drc_power_domains->data,
drc_power_domains->len * sizeof(uint32_t));
if (ret) {
error_report("Couldn't finalize ibm,drc-power-domains property");
goto out;
}
ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-names",
drc_names->str, drc_names->len);
if (ret) {
error_report("Couldn't finalize ibm,drc-names property");
goto out;
}
ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-types",
drc_types->str, drc_types->len);
if (ret) {
error_report("Couldn't finalize ibm,drc-types property");
goto out;
}
out:
g_array_free(drc_indexes, true);
g_array_free(drc_power_domains, true);
g_string_free(drc_names, true);
g_string_free(drc_types, true);
return ret;
}
/*
* RTAS calls
*/
static uint32_t rtas_set_isolation_state(uint32_t idx, uint32_t state)
{
sPAPRDRConnector *drc = spapr_drc_by_index(idx);
sPAPRDRConnectorClass *drck;
if (!drc) {
return RTAS_OUT_NO_SUCH_INDICATOR;
}
trace_spapr_drc_set_isolation_state(spapr_drc_index(drc), state);
drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
switch (state) {
case SPAPR_DR_ISOLATION_STATE_ISOLATED:
return drck->isolate(drc);
case SPAPR_DR_ISOLATION_STATE_UNISOLATED:
return drck->unisolate(drc);
default:
return RTAS_OUT_PARAM_ERROR;
}
}
static uint32_t rtas_set_allocation_state(uint32_t idx, uint32_t state)
{
sPAPRDRConnector *drc = spapr_drc_by_index(idx);
if (!drc || !object_dynamic_cast(OBJECT(drc), TYPE_SPAPR_DRC_LOGICAL)) {
return RTAS_OUT_NO_SUCH_INDICATOR;
}
trace_spapr_drc_set_allocation_state(spapr_drc_index(drc), state);
switch (state) {
case SPAPR_DR_ALLOCATION_STATE_USABLE:
return drc_set_usable(drc);
case SPAPR_DR_ALLOCATION_STATE_UNUSABLE:
return drc_set_unusable(drc);
default:
return RTAS_OUT_PARAM_ERROR;
}
}
static uint32_t rtas_set_dr_indicator(uint32_t idx, uint32_t state)
{
sPAPRDRConnector *drc = spapr_drc_by_index(idx);
if (!drc || !object_dynamic_cast(OBJECT(drc), TYPE_SPAPR_DRC_PHYSICAL)) {
return RTAS_OUT_NO_SUCH_INDICATOR;
}
if ((state != SPAPR_DR_INDICATOR_INACTIVE)
&& (state != SPAPR_DR_INDICATOR_ACTIVE)
&& (state != SPAPR_DR_INDICATOR_IDENTIFY)
&& (state != SPAPR_DR_INDICATOR_ACTION)) {
return RTAS_OUT_PARAM_ERROR; /* bad state parameter */
}
trace_spapr_drc_set_dr_indicator(idx, state);
SPAPR_DRC_PHYSICAL(drc)->dr_indicator = state;
return RTAS_OUT_SUCCESS;
}
static void rtas_set_indicator(PowerPCCPU *cpu, sPAPRMachineState *spapr,
uint32_t token,
uint32_t nargs, target_ulong args,
uint32_t nret, target_ulong rets)
{
uint32_t type, idx, state;
uint32_t ret = RTAS_OUT_SUCCESS;
if (nargs != 3 || nret != 1) {
ret = RTAS_OUT_PARAM_ERROR;
goto out;
}
type = rtas_ld(args, 0);
idx = rtas_ld(args, 1);
state = rtas_ld(args, 2);
switch (type) {
case RTAS_SENSOR_TYPE_ISOLATION_STATE:
ret = rtas_set_isolation_state(idx, state);
break;
case RTAS_SENSOR_TYPE_DR:
ret = rtas_set_dr_indicator(idx, state);
break;
case RTAS_SENSOR_TYPE_ALLOCATION_STATE:
ret = rtas_set_allocation_state(idx, state);
break;
default:
ret = RTAS_OUT_NOT_SUPPORTED;
}
out:
rtas_st(rets, 0, ret);
}
static void rtas_get_sensor_state(PowerPCCPU *cpu, sPAPRMachineState *spapr,
uint32_t token, uint32_t nargs,
target_ulong args, uint32_t nret,
target_ulong rets)
{
uint32_t sensor_type;
uint32_t sensor_index;
uint32_t sensor_state = 0;
sPAPRDRConnector *drc;
sPAPRDRConnectorClass *drck;
uint32_t ret = RTAS_OUT_SUCCESS;
if (nargs != 2 || nret != 2) {
ret = RTAS_OUT_PARAM_ERROR;
goto out;
}
sensor_type = rtas_ld(args, 0);
sensor_index = rtas_ld(args, 1);
if (sensor_type != RTAS_SENSOR_TYPE_ENTITY_SENSE) {
/* currently only DR-related sensors are implemented */
trace_spapr_rtas_get_sensor_state_not_supported(sensor_index,
sensor_type);
ret = RTAS_OUT_NOT_SUPPORTED;
goto out;
}
drc = spapr_drc_by_index(sensor_index);
if (!drc) {
trace_spapr_rtas_get_sensor_state_invalid(sensor_index);
ret = RTAS_OUT_PARAM_ERROR;
goto out;
}
drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
sensor_state = drck->dr_entity_sense(drc);
out:
rtas_st(rets, 0, ret);
rtas_st(rets, 1, sensor_state);
}
/* configure-connector work area offsets, int32_t units for field
* indexes, bytes for field offset/len values.
*
* as documented by PAPR+ v2.7, 13.5.3.5
*/
#define CC_IDX_NODE_NAME_OFFSET 2
#define CC_IDX_PROP_NAME_OFFSET 2
#define CC_IDX_PROP_LEN 3
#define CC_IDX_PROP_DATA_OFFSET 4
#define CC_VAL_DATA_OFFSET ((CC_IDX_PROP_DATA_OFFSET + 1) * 4)
#define CC_WA_LEN 4096
static void configure_connector_st(target_ulong addr, target_ulong offset,
const void *buf, size_t len)
{
cpu_physical_memory_write(ppc64_phys_to_real(addr + offset),
buf, MIN(len, CC_WA_LEN - offset));
}
static void rtas_ibm_configure_connector(PowerPCCPU *cpu,
sPAPRMachineState *spapr,
uint32_t token, uint32_t nargs,
target_ulong args, uint32_t nret,
target_ulong rets)
{
uint64_t wa_addr;
uint64_t wa_offset;
uint32_t drc_index;
sPAPRDRConnector *drc;
sPAPRDRConnectorClass *drck;
sPAPRDRCCResponse resp = SPAPR_DR_CC_RESPONSE_CONTINUE;
int rc;
if (nargs != 2 || nret != 1) {
rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
return;
}
wa_addr = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 0);
drc_index = rtas_ld(wa_addr, 0);
drc = spapr_drc_by_index(drc_index);
if (!drc) {
trace_spapr_rtas_ibm_configure_connector_invalid(drc_index);
rc = RTAS_OUT_PARAM_ERROR;
goto out;
}
if ((drc->state != SPAPR_DRC_STATE_LOGICAL_UNISOLATE)
&& (drc->state != SPAPR_DRC_STATE_PHYSICAL_UNISOLATE)
&& (drc->state != SPAPR_DRC_STATE_LOGICAL_CONFIGURED)
&& (drc->state != SPAPR_DRC_STATE_PHYSICAL_CONFIGURED)) {
/*
* Need to unisolate the device before configuring
* or it should already be in configured state to
* allow configure-connector be called repeatedly.
*/
rc = SPAPR_DR_CC_RESPONSE_NOT_CONFIGURABLE;
goto out;
}
drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
spapr_drc: Allow FDT fragment to be added later The current logic is to provide the FDT fragment when attaching a device to a DRC. This works perfectly fine for our current hotplug support, but soon we will add support for PHB hotplug which has some constraints, that CPU, PCI and LMB devices don't seem to have. The first constraint is that the "ibm,dma-window" property of the PHB node requires the IOMMU to be configured, ie, spapr_tce_table_enable() has been called, which happens during PHB reset. It is okay in the case of hotplug since the device is reset before the hotplug handler is called. On the contrary with coldplug, the hotplug handler is called first and device is only reset during the initial system reset. Trying to create the FDT fragment on the hotplug path in this case, would result in somthing like this: ibm,dma-window = < 0x80000000 0x00 0x00 0x00 0x00 >; This will cause linux in the guest to panic, by simply removing and re-adding the PHB using the drmgr command: page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz)); if (!page) panic("iommu_init_table: Can't allocate %ld bytes\n", sz); The second and maybe more problematic constraint is that the "interrupt-map" property needs to reference the interrupt controller node using the very same phandle that SLOF has already exposed to the guest. QEMU requires SLOF to call the private KVMPPC_H_UPDATE_DT hcall at some point to know about this phandle. With the latest QEMU and SLOF, this happens when SLOF gets quiesced. This means that if the PHB gets hotplugged after CAS but before SLOF quiesce, then we're sure that the phandle is not known when the hotplug handler is called. The FDT is only needed when the guest first invokes RTAS to configure the connector actually, long after SLOF quiesce. Let's postpone the creation of FDT fragments for PHBs to rtas_ibm_configure_connector(). Since we only need this for PHBs, introduce a new method in the base DRC class for that. DRC subtypes will be converted to use it in subsequent patches. Allow spapr_drc_attach() to be passed a NULL fdt argument if the method is available. When all DRC subtypes have been converted, the fdt argument will eventually disappear. Signed-off-by: Greg Kurz <groug@kaod.org> Message-Id: <155059665823.1466090.18358845122627355537.stgit@bahia.lab.toulouse-stg.fr.ibm.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2019-02-19 20:17:38 +03:00
if (!drc->fdt) {
Error *local_err = NULL;
void *fdt;
int fdt_size;
fdt = create_device_tree(&fdt_size);
if (drck->dt_populate(drc, spapr, fdt, &drc->fdt_start_offset,
&local_err)) {
g_free(fdt);
error_free(local_err);
rc = SPAPR_DR_CC_RESPONSE_ERROR;
goto out;
}
drc->fdt = fdt;
drc->ccs_offset = drc->fdt_start_offset;
drc->ccs_depth = 0;
}
do {
uint32_t tag;
const char *name;
const struct fdt_property *prop;
int fdt_offset_next, prop_len;
spapr: Remove sPAPRConfigureConnectorState sub-structure Most of the time, the state of a DRC object is contained in the single 'state' variable. However, during the transition from UNISOLATE to CONFIGURED state requires multiple calls to the ibm,configure-connector RTAS call to retrieve the device tree for the attached device. We need some extra state to keep track of where we're up to in delivering the device tree information to the guest. Currently that extra state is in a sPAPRConfigureConnectorState substructure which is only allocated when we're in the middle of the configure connector process. That sounds like a good idea, but the extra state is only two integers - on many platforms that will take up the same room as the (maybe NULL) ccs pointer even before malloc() overhead. Plus it's another object whose lifetime we need to manage. In short, it's not worth it. So, fold the sPAPRConfigureConnectorState substructure directly into the DRC object. Previously the structure was allocated lazily when the configure-connector call discovers it's not there. Now, we need to initialize the subfields pre-emptively, as soon as we enter UNISOLATE state. Although it's not strictly necessary (the field values should only ever be consulted when in UNISOLATE state), we try to keep them at -1 when in other states, as a debugging aid. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Daniel Barboza <danielhb@linux.vnet.ibm.com> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-21 12:12:14 +03:00
tag = fdt_next_tag(drc->fdt, drc->ccs_offset, &fdt_offset_next);
switch (tag) {
case FDT_BEGIN_NODE:
spapr: Remove sPAPRConfigureConnectorState sub-structure Most of the time, the state of a DRC object is contained in the single 'state' variable. However, during the transition from UNISOLATE to CONFIGURED state requires multiple calls to the ibm,configure-connector RTAS call to retrieve the device tree for the attached device. We need some extra state to keep track of where we're up to in delivering the device tree information to the guest. Currently that extra state is in a sPAPRConfigureConnectorState substructure which is only allocated when we're in the middle of the configure connector process. That sounds like a good idea, but the extra state is only two integers - on many platforms that will take up the same room as the (maybe NULL) ccs pointer even before malloc() overhead. Plus it's another object whose lifetime we need to manage. In short, it's not worth it. So, fold the sPAPRConfigureConnectorState substructure directly into the DRC object. Previously the structure was allocated lazily when the configure-connector call discovers it's not there. Now, we need to initialize the subfields pre-emptively, as soon as we enter UNISOLATE state. Although it's not strictly necessary (the field values should only ever be consulted when in UNISOLATE state), we try to keep them at -1 when in other states, as a debugging aid. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Daniel Barboza <danielhb@linux.vnet.ibm.com> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-21 12:12:14 +03:00
drc->ccs_depth++;
name = fdt_get_name(drc->fdt, drc->ccs_offset, NULL);
/* provide the name of the next OF node */
wa_offset = CC_VAL_DATA_OFFSET;
rtas_st(wa_addr, CC_IDX_NODE_NAME_OFFSET, wa_offset);
configure_connector_st(wa_addr, wa_offset, name, strlen(name) + 1);
resp = SPAPR_DR_CC_RESPONSE_NEXT_CHILD;
break;
case FDT_END_NODE:
spapr: Remove sPAPRConfigureConnectorState sub-structure Most of the time, the state of a DRC object is contained in the single 'state' variable. However, during the transition from UNISOLATE to CONFIGURED state requires multiple calls to the ibm,configure-connector RTAS call to retrieve the device tree for the attached device. We need some extra state to keep track of where we're up to in delivering the device tree information to the guest. Currently that extra state is in a sPAPRConfigureConnectorState substructure which is only allocated when we're in the middle of the configure connector process. That sounds like a good idea, but the extra state is only two integers - on many platforms that will take up the same room as the (maybe NULL) ccs pointer even before malloc() overhead. Plus it's another object whose lifetime we need to manage. In short, it's not worth it. So, fold the sPAPRConfigureConnectorState substructure directly into the DRC object. Previously the structure was allocated lazily when the configure-connector call discovers it's not there. Now, we need to initialize the subfields pre-emptively, as soon as we enter UNISOLATE state. Although it's not strictly necessary (the field values should only ever be consulted when in UNISOLATE state), we try to keep them at -1 when in other states, as a debugging aid. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Daniel Barboza <danielhb@linux.vnet.ibm.com> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-21 12:12:14 +03:00
drc->ccs_depth--;
if (drc->ccs_depth == 0) {
uint32_t drc_index = spapr_drc_index(drc);
/* done sending the device tree, move to configured state */
trace_spapr_drc_set_configured(drc_index);
drc->state = drck->ready_state;
/*
* Ensure that we are able to send the FDT fragment
* again via configure-connector call if the guest requests.
*/
drc->ccs_offset = drc->fdt_start_offset;
drc->ccs_depth = 0;
fdt_offset_next = drc->fdt_start_offset;
resp = SPAPR_DR_CC_RESPONSE_SUCCESS;
} else {
resp = SPAPR_DR_CC_RESPONSE_PREV_PARENT;
}
break;
case FDT_PROP:
spapr: Remove sPAPRConfigureConnectorState sub-structure Most of the time, the state of a DRC object is contained in the single 'state' variable. However, during the transition from UNISOLATE to CONFIGURED state requires multiple calls to the ibm,configure-connector RTAS call to retrieve the device tree for the attached device. We need some extra state to keep track of where we're up to in delivering the device tree information to the guest. Currently that extra state is in a sPAPRConfigureConnectorState substructure which is only allocated when we're in the middle of the configure connector process. That sounds like a good idea, but the extra state is only two integers - on many platforms that will take up the same room as the (maybe NULL) ccs pointer even before malloc() overhead. Plus it's another object whose lifetime we need to manage. In short, it's not worth it. So, fold the sPAPRConfigureConnectorState substructure directly into the DRC object. Previously the structure was allocated lazily when the configure-connector call discovers it's not there. Now, we need to initialize the subfields pre-emptively, as soon as we enter UNISOLATE state. Although it's not strictly necessary (the field values should only ever be consulted when in UNISOLATE state), we try to keep them at -1 when in other states, as a debugging aid. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Daniel Barboza <danielhb@linux.vnet.ibm.com> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-21 12:12:14 +03:00
prop = fdt_get_property_by_offset(drc->fdt, drc->ccs_offset,
&prop_len);
name = fdt_string(drc->fdt, fdt32_to_cpu(prop->nameoff));
/* provide the name of the next OF property */
wa_offset = CC_VAL_DATA_OFFSET;
rtas_st(wa_addr, CC_IDX_PROP_NAME_OFFSET, wa_offset);
configure_connector_st(wa_addr, wa_offset, name, strlen(name) + 1);
/* provide the length and value of the OF property. data gets
* placed immediately after NULL terminator of the OF property's
* name string
*/
wa_offset += strlen(name) + 1,
rtas_st(wa_addr, CC_IDX_PROP_LEN, prop_len);
rtas_st(wa_addr, CC_IDX_PROP_DATA_OFFSET, wa_offset);
configure_connector_st(wa_addr, wa_offset, prop->data, prop_len);
resp = SPAPR_DR_CC_RESPONSE_NEXT_PROPERTY;
break;
case FDT_END:
resp = SPAPR_DR_CC_RESPONSE_ERROR;
default:
/* keep seeking for an actionable tag */
break;
}
spapr: Remove sPAPRConfigureConnectorState sub-structure Most of the time, the state of a DRC object is contained in the single 'state' variable. However, during the transition from UNISOLATE to CONFIGURED state requires multiple calls to the ibm,configure-connector RTAS call to retrieve the device tree for the attached device. We need some extra state to keep track of where we're up to in delivering the device tree information to the guest. Currently that extra state is in a sPAPRConfigureConnectorState substructure which is only allocated when we're in the middle of the configure connector process. That sounds like a good idea, but the extra state is only two integers - on many platforms that will take up the same room as the (maybe NULL) ccs pointer even before malloc() overhead. Plus it's another object whose lifetime we need to manage. In short, it's not worth it. So, fold the sPAPRConfigureConnectorState substructure directly into the DRC object. Previously the structure was allocated lazily when the configure-connector call discovers it's not there. Now, we need to initialize the subfields pre-emptively, as soon as we enter UNISOLATE state. Although it's not strictly necessary (the field values should only ever be consulted when in UNISOLATE state), we try to keep them at -1 when in other states, as a debugging aid. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Daniel Barboza <danielhb@linux.vnet.ibm.com> Tested-by: Daniel Barboza <danielhb@linux.vnet.ibm.com>
2017-06-21 12:12:14 +03:00
if (drc->ccs_offset >= 0) {
drc->ccs_offset = fdt_offset_next;
}
} while (resp == SPAPR_DR_CC_RESPONSE_CONTINUE);
rc = resp;
out:
rtas_st(rets, 0, rc);
}
static void spapr_drc_register_types(void)
{
type_register_static(&spapr_dr_connector_info);
type_register_static(&spapr_drc_physical_info);
type_register_static(&spapr_drc_logical_info);
type_register_static(&spapr_drc_cpu_info);
type_register_static(&spapr_drc_pci_info);
type_register_static(&spapr_drc_lmb_info);
type_register_static(&spapr_drc_phb_info);
spapr_rtas_register(RTAS_SET_INDICATOR, "set-indicator",
rtas_set_indicator);
spapr_rtas_register(RTAS_GET_SENSOR_STATE, "get-sensor-state",
rtas_get_sensor_state);
spapr_rtas_register(RTAS_IBM_CONFIGURE_CONNECTOR, "ibm,configure-connector",
rtas_ibm_configure_connector);
}
type_init(spapr_drc_register_types)