spapr_events: re-use EPOW event infrastructure for hotplug events

This extends the data structures currently used to report EPOW events to
guests via the check-exception RTAS interfaces to also include event types
for hotplug/unplug events.

This is currently undocumented and being finalized for inclusion in PAPR
specification, but we implement this here as an extension for guest
userspace tools to implement (existing guest kernels simply log these
events via a sysfs interface that's read by rtas_errd, and current
versions of rtas_errd/powerpc-utils already support the use of this
mechanism for initiating hotplug operations).

We also add support for queues of pending RTAS events, since in the
case of hotplug there's chance for multiple events being in-flight
at any point in time.

Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexander Graf <agraf@suse.de>

3 files changed, 252 insertions, 52 deletions

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 7323efda4c..15eebb4b2d 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1660,7 +1660,8 @@ static void ppc_spapr_init(MachineState *machine)
     /* Prepare the device tree */
     spapr->fdt_skel = spapr_create_fdt_skel(initrd_base, initrd_size,
                                             kernel_size, kernel_le,
-                                            kernel_cmdline, spapr->epow_irq);
+                                            kernel_cmdline,
+                                            spapr->check_exception_irq);
     assert(spapr->fdt_skel != NULL);
 
     /* used by RTAS */
diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
index 283e96bca1..c634a3b435 100644
--- a/hw/ppc/spapr_events.c
+++ b/hw/ppc/spapr_events.c
@@ -32,6 +32,9 @@
 
 #include "hw/ppc/spapr.h"
 #include "hw/ppc/spapr_vio.h"
+#include "hw/pci/pci.h"
+#include "hw/pci-host/spapr.h"
+#include "hw/ppc/spapr_drc.h"
 
 #include <libfdt.h>
 
@@ -77,6 +80,7 @@ struct rtas_error_log {
 #define   RTAS_LOG_TYPE_ECC_UNCORR              0x00000009
 #define   RTAS_LOG_TYPE_ECC_CORR                0x0000000a
 #define   RTAS_LOG_TYPE_EPOW                    0x00000040
+#define   RTAS_LOG_TYPE_HOTPLUG                 0x000000e5
     uint32_t extended_length;
 } QEMU_PACKED;
 
@@ -166,6 +170,38 @@ struct epow_log_full {
     struct rtas_event_log_v6_epow epow;
 } QEMU_PACKED;
 
+struct rtas_event_log_v6_hp {
+#define RTAS_LOG_V6_SECTION_ID_HOTPLUG              0x4850 /* HP */
+    struct rtas_event_log_v6_section_header hdr;
+    uint8_t hotplug_type;
+#define RTAS_LOG_V6_HP_TYPE_CPU                          1
+#define RTAS_LOG_V6_HP_TYPE_MEMORY                       2
+#define RTAS_LOG_V6_HP_TYPE_SLOT                         3
+#define RTAS_LOG_V6_HP_TYPE_PHB                          4
+#define RTAS_LOG_V6_HP_TYPE_PCI                          5
+    uint8_t hotplug_action;
+#define RTAS_LOG_V6_HP_ACTION_ADD                        1
+#define RTAS_LOG_V6_HP_ACTION_REMOVE                     2
+    uint8_t hotplug_identifier;
+#define RTAS_LOG_V6_HP_ID_DRC_NAME                       1
+#define RTAS_LOG_V6_HP_ID_DRC_INDEX                      2
+#define RTAS_LOG_V6_HP_ID_DRC_COUNT                      3
+    uint8_t reserved;
+    union {
+        uint32_t index;
+        uint32_t count;
+        char name[1];
+    } drc;
+} QEMU_PACKED;
+
+struct hp_log_full {
+    struct rtas_error_log hdr;
+    struct rtas_event_log_v6 v6hdr;
+    struct rtas_event_log_v6_maina maina;
+    struct rtas_event_log_v6_mainb mainb;
+    struct rtas_event_log_v6_hp hp;
+} QEMU_PACKED;
+
 #define EVENT_MASK_INTERNAL_ERRORS           0x80000000
 #define EVENT_MASK_EPOW                      0x40000000
 #define EVENT_MASK_HOTPLUG                   0x10000000
@@ -181,67 +217,95 @@ struct epow_log_full {
         }                                                          \
     } while (0)
 
-void spapr_events_fdt_skel(void *fdt, uint32_t epow_irq)
+void spapr_events_fdt_skel(void *fdt, uint32_t check_exception_irq)
 {
-    uint32_t epow_irq_ranges[] = {cpu_to_be32(epow_irq), cpu_to_be32(1)};
-    uint32_t epow_interrupts[] = {cpu_to_be32(epow_irq), 0};
+    uint32_t irq_ranges[] = {cpu_to_be32(check_exception_irq), cpu_to_be32(1)};
+    uint32_t interrupts[] = {cpu_to_be32(check_exception_irq), 0};
 
     _FDT((fdt_begin_node(fdt, "event-sources")));
 
     _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
     _FDT((fdt_property_cell(fdt, "#interrupt-cells", 2)));
     _FDT((fdt_property(fdt, "interrupt-ranges",
-                       epow_irq_ranges, sizeof(epow_irq_ranges))));
+                       irq_ranges, sizeof(irq_ranges))));
 
     _FDT((fdt_begin_node(fdt, "epow-events")));
-    _FDT((fdt_property(fdt, "interrupts",
-                       epow_interrupts, sizeof(epow_interrupts))));
+    _FDT((fdt_property(fdt, "interrupts", interrupts, sizeof(interrupts))));
     _FDT((fdt_end_node(fdt)));
 
     _FDT((fdt_end_node(fdt)));
 }
 
-static struct epow_log_full *pending_epow;
-static uint32_t next_plid;
+static void rtas_event_log_queue(int log_type, void *data)
+{
+    sPAPREventLogEntry *entry = g_new(sPAPREventLogEntry, 1);
 
-static void spapr_powerdown_req(Notifier *n, void *opaque)
+    g_assert(data);
+    entry->log_type = log_type;
+    entry->data = data;
+    QTAILQ_INSERT_TAIL(&spapr->pending_events, entry, next);
+}
+
+static sPAPREventLogEntry *rtas_event_log_dequeue(uint32_t event_mask)
 {
-    sPAPREnvironment *spapr = container_of(n, sPAPREnvironment, epow_notifier);
-    struct rtas_error_log *hdr;
-    struct rtas_event_log_v6 *v6hdr;
-    struct rtas_event_log_v6_maina *maina;
-    struct rtas_event_log_v6_mainb *mainb;
-    struct rtas_event_log_v6_epow *epow;
-    struct tm tm;
-    int year;
+    sPAPREventLogEntry *entry = NULL;
 
-    if (pending_epow) {
-        /* For now, we just throw away earlier events if two come
-         * along before any are consumed.  This is sufficient for our
-         * powerdown messages, but we'll need more if we do more
-         * general error/event logging */
-        g_free(pending_epow);
+    /* we only queue EPOW events atm. */
+    if ((event_mask & EVENT_MASK_EPOW) == 0) {
+        return NULL;
     }
-    pending_epow = g_malloc0(sizeof(*pending_epow));
-    hdr = &pending_epow->hdr;
-    v6hdr = &pending_epow->v6hdr;
-    maina = &pending_epow->maina;
-    mainb = &pending_epow->mainb;
-    epow = &pending_epow->epow;
 
-    hdr->summary = cpu_to_be32(RTAS_LOG_VERSION_6
-                               | RTAS_LOG_SEVERITY_EVENT
-                               | RTAS_LOG_DISPOSITION_NOT_RECOVERED
-                               | RTAS_LOG_OPTIONAL_PART_PRESENT
-                               | RTAS_LOG_TYPE_EPOW);
-    hdr->extended_length = cpu_to_be32(sizeof(*pending_epow)
-                                       - sizeof(pending_epow->hdr));
+    QTAILQ_FOREACH(entry, &spapr->pending_events, next) {
+        /* EPOW and hotplug events are surfaced in the same manner */
+        if (entry->log_type == RTAS_LOG_TYPE_EPOW ||
+            entry->log_type == RTAS_LOG_TYPE_HOTPLUG) {
+            break;
+        }
+    }
+
+    if (entry) {
+        QTAILQ_REMOVE(&spapr->pending_events, entry, next);
+    }
+
+    return entry;
+}
+
+static bool rtas_event_log_contains(uint32_t event_mask)
+{
+    sPAPREventLogEntry *entry = NULL;
+
+    /* we only queue EPOW events atm. */
+    if ((event_mask & EVENT_MASK_EPOW) == 0) {
+        return false;
+    }
+
+    QTAILQ_FOREACH(entry, &spapr->pending_events, next) {
+        /* EPOW and hotplug events are surfaced in the same manner */
+        if (entry->log_type == RTAS_LOG_TYPE_EPOW ||
+            entry->log_type == RTAS_LOG_TYPE_HOTPLUG) {
+            return true;
+        }
+    }
+
+    return false;
+}
 
+static uint32_t next_plid;
+
+static void spapr_init_v6hdr(struct rtas_event_log_v6 *v6hdr)
+{
     v6hdr->b0 = RTAS_LOG_V6_B0_VALID | RTAS_LOG_V6_B0_NEW_LOG
         | RTAS_LOG_V6_B0_BIGENDIAN;
     v6hdr->b2 = RTAS_LOG_V6_B2_POWERPC_FORMAT
         | RTAS_LOG_V6_B2_LOG_FORMAT_PLATFORM_EVENT;
     v6hdr->company = cpu_to_be32(RTAS_LOG_V6_COMPANY_IBM);
+}
+
+static void spapr_init_maina(struct rtas_event_log_v6_maina *maina,
+                             int section_count)
+{
+    struct tm tm;
+    int year;
 
     maina->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MAINA);
     maina->hdr.section_length = cpu_to_be16(sizeof(*maina));
@@ -256,8 +320,37 @@ static void spapr_powerdown_req(Notifier *n, void *opaque)
                                        | (to_bcd(tm.tm_min) << 16)
                                        | (to_bcd(tm.tm_sec) << 8));
     maina->creator_id = 'H'; /* Hypervisor */
-    maina->section_count = 3; /* Main-A, Main-B and EPOW */
+    maina->section_count = section_count;
     maina->plid = next_plid++;
+}
+
+static void spapr_powerdown_req(Notifier *n, void *opaque)
+{
+    sPAPREnvironment *spapr = container_of(n, sPAPREnvironment, epow_notifier);
+    struct rtas_error_log *hdr;
+    struct rtas_event_log_v6 *v6hdr;
+    struct rtas_event_log_v6_maina *maina;
+    struct rtas_event_log_v6_mainb *mainb;
+    struct rtas_event_log_v6_epow *epow;
+    struct epow_log_full *new_epow;
+
+    new_epow = g_malloc0(sizeof(*new_epow));
+    hdr = &new_epow->hdr;
+    v6hdr = &new_epow->v6hdr;
+    maina = &new_epow->maina;
+    mainb = &new_epow->mainb;
+    epow = &new_epow->epow;
+
+    hdr->summary = cpu_to_be32(RTAS_LOG_VERSION_6
+                               | RTAS_LOG_SEVERITY_EVENT
+                               | RTAS_LOG_DISPOSITION_NOT_RECOVERED
+                               | RTAS_LOG_OPTIONAL_PART_PRESENT
+                               | RTAS_LOG_TYPE_EPOW);
+    hdr->extended_length = cpu_to_be32(sizeof(*new_epow)
+                                       - sizeof(new_epow->hdr));
+
+    spapr_init_v6hdr(v6hdr);
+    spapr_init_maina(maina, 3 /* Main-A, Main-B and EPOW */);
 
     mainb->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MAINB);
     mainb->hdr.section_length = cpu_to_be16(sizeof(*mainb));
@@ -274,7 +367,80 @@ static void spapr_powerdown_req(Notifier *n, void *opaque)
     epow->event_modifier = RTAS_LOG_V6_EPOW_MODIFIER_NORMAL;
     epow->extended_modifier = RTAS_LOG_V6_EPOW_XMODIFIER_PARTITION_SPECIFIC;
 
-    qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->epow_irq));
+    rtas_event_log_queue(RTAS_LOG_TYPE_EPOW, new_epow);
+
+    qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->check_exception_irq));
+}
+
+static void spapr_hotplug_req_event(sPAPRDRConnector *drc, uint8_t hp_action)
+{
+    struct hp_log_full *new_hp;
+    struct rtas_error_log *hdr;
+    struct rtas_event_log_v6 *v6hdr;
+    struct rtas_event_log_v6_maina *maina;
+    struct rtas_event_log_v6_mainb *mainb;
+    struct rtas_event_log_v6_hp *hp;
+    sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+    sPAPRDRConnectorType drc_type = drck->get_type(drc);
+
+    new_hp = g_malloc0(sizeof(struct hp_log_full));
+    hdr = &new_hp->hdr;
+    v6hdr = &new_hp->v6hdr;
+    maina = &new_hp->maina;
+    mainb = &new_hp->mainb;
+    hp = &new_hp->hp;
+
+    hdr->summary = cpu_to_be32(RTAS_LOG_VERSION_6
+                               | RTAS_LOG_SEVERITY_EVENT
+                               | RTAS_LOG_DISPOSITION_NOT_RECOVERED
+                               | RTAS_LOG_OPTIONAL_PART_PRESENT
+                               | RTAS_LOG_INITIATOR_HOTPLUG
+                               | RTAS_LOG_TYPE_HOTPLUG);
+    hdr->extended_length = cpu_to_be32(sizeof(*new_hp)
+                                       - sizeof(new_hp->hdr));
+
+    spapr_init_v6hdr(v6hdr);
+    spapr_init_maina(maina, 3 /* Main-A, Main-B, HP */);
+
+    mainb->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MAINB);
+    mainb->hdr.section_length = cpu_to_be16(sizeof(*mainb));
+    mainb->subsystem_id = 0x80; /* External environment */
+    mainb->event_severity = 0x00; /* Informational / non-error */
+    mainb->event_subtype = 0x00; /* Normal shutdown */
+
+    hp->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_HOTPLUG);
+    hp->hdr.section_length = cpu_to_be16(sizeof(*hp));
+    hp->hdr.section_version = 1; /* includes extended modifier */
+    hp->hotplug_action = hp_action;
+
+
+    switch (drc_type) {
+    case SPAPR_DR_CONNECTOR_TYPE_PCI:
+        hp->drc.index = cpu_to_be32(drck->get_index(drc));
+        hp->hotplug_identifier = RTAS_LOG_V6_HP_ID_DRC_INDEX;
+        hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_PCI;
+        break;
+    default:
+        /* we shouldn't be signaling hotplug events for resources
+         * that don't support them
+         */
+        g_assert(false);
+        return;
+    }
+
+    rtas_event_log_queue(RTAS_LOG_TYPE_HOTPLUG, new_hp);
+
+    qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->check_exception_irq));
+}
+
+void spapr_hotplug_req_add_event(sPAPRDRConnector *drc)
+{
+    spapr_hotplug_req_event(drc, RTAS_LOG_V6_HP_ACTION_ADD);
+}
+
+void spapr_hotplug_req_remove_event(sPAPRDRConnector *drc)
+{
+    spapr_hotplug_req_event(drc, RTAS_LOG_V6_HP_ACTION_REMOVE);
 }
 
 static void check_exception(PowerPCCPU *cpu, sPAPREnvironment *spapr,
@@ -282,8 +448,10 @@ static void check_exception(PowerPCCPU *cpu, sPAPREnvironment *spapr,
                             target_ulong args,
                             uint32_t nret, target_ulong rets)
 {
-    uint32_t mask, buf, len;
+    uint32_t mask, buf, len, event_len;
     uint64_t xinfo;
+    sPAPREventLogEntry *event;
+    struct rtas_error_log *hdr;
 
     if ((nargs < 6) || (nargs > 7) || nret != 1) {
         rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
@@ -298,23 +466,42 @@ static void check_exception(PowerPCCPU *cpu, sPAPREnvironment *spapr,
         xinfo |= (uint64_t)rtas_ld(args, 6) << 32;
     }
 
-    if ((mask & EVENT_MASK_EPOW) && pending_epow) {
-        if (sizeof(*pending_epow) < len) {
-            len = sizeof(*pending_epow);
-        }
+    event = rtas_event_log_dequeue(mask);
+    if (!event) {
+        goto out_no_events;
+    }
 
-        cpu_physical_memory_write(buf, pending_epow, len);
-        g_free(pending_epow);
-        pending_epow = NULL;
-        rtas_st(rets, 0, RTAS_OUT_SUCCESS);
-    } else {
-        rtas_st(rets, 0, RTAS_OUT_NO_ERRORS_FOUND);
+    hdr = event->data;
+    event_len = be32_to_cpu(hdr->extended_length) + sizeof(*hdr);
+
+    if (event_len < len) {
+        len = event_len;
+    }
+
+    cpu_physical_memory_write(buf, event->data, len);
+    rtas_st(rets, 0, RTAS_OUT_SUCCESS);
+    g_free(event->data);
+    g_free(event);
+
+    /* according to PAPR+, the IRQ must be left asserted, or re-asserted, if
+     * there are still pending events to be fetched via check-exception. We
+     * do the latter here, since our code relies on edge-triggered
+     * interrupts.
+     */
+    if (rtas_event_log_contains(mask)) {
+        qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->check_exception_irq));
     }
+
+    return;
+
+out_no_events:
+    rtas_st(rets, 0, RTAS_OUT_NO_ERRORS_FOUND);
 }
 
 void spapr_events_init(sPAPREnvironment *spapr)
 {
-    spapr->epow_irq = xics_alloc(spapr->icp, 0, 0, false);
+    QTAILQ_INIT(&spapr->pending_events);
+    spapr->check_exception_irq = xics_alloc(spapr->icp, 0, 0, false);
     spapr->epow_notifier.notify = spapr_powerdown_req;
     qemu_register_powerdown_notifier(&spapr->epow_notifier);
     spapr_rtas_register(RTAS_CHECK_EXCEPTION, "check-exception",
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 86221934c8..71b3e0876b 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -3,11 +3,13 @@
 
 #include "sysemu/dma.h"
 #include "hw/ppc/xics.h"
+#include "hw/ppc/spapr_drc.h"
 
 struct VIOsPAPRBus;
 struct sPAPRPHBState;
 struct sPAPRNVRAM;
 typedef struct sPAPRConfigureConnectorState sPAPRConfigureConnectorState;
+typedef struct sPAPREventLogEntry sPAPREventLogEntry;
 
 #define HPTE64_V_HPTE_DIRTY     0x0000000000000040ULL
 
@@ -32,8 +34,9 @@ typedef struct sPAPREnvironment {
     struct PPCTimebase tb;
     bool has_graphics;
 
-    uint32_t epow_irq;
+    uint32_t check_exception_irq;
     Notifier epow_notifier;
+    QTAILQ_HEAD(, sPAPREventLogEntry) pending_events;
 
     /* Migration state */
     int htab_save_index;
@@ -533,6 +536,13 @@ struct sPAPRTCETable {
 };
 
 sPAPRTCETable *spapr_tce_find_by_liobn(target_ulong liobn);
+
+struct sPAPREventLogEntry {
+    int log_type;
+    void *data;
+    QTAILQ_ENTRY(sPAPREventLogEntry) next;
+};
+
 void spapr_events_init(sPAPREnvironment *spapr);
 void spapr_events_fdt_skel(void *fdt, uint32_t epow_irq);
 int spapr_h_cas_compose_response(target_ulong addr, target_ulong size);
@@ -547,6 +557,8 @@ int spapr_dma_dt(void *fdt, int node_off, const char *propname,
 int spapr_tcet_dma_dt(void *fdt, int node_off, const char *propname,
                       sPAPRTCETable *tcet);
 void spapr_pci_switch_vga(bool big_endian);
+void spapr_hotplug_req_add_event(sPAPRDRConnector *drc);
+void spapr_hotplug_req_remove_event(sPAPRDRConnector *drc);
 
 /* rtas-configure-connector state */
 struct sPAPRConfigureConnectorState {