Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-5.1-20200507' into staging

ppc patch queue for 2020-04-07

First pull request for qemu-5.1.  This includes:
 * Removal of all remaining cases where we had CAS triggered reboots
 * A number of improvements to NMI injection
 * Support for partition scoped radix translation in softmmu
 * Some fixes for NVDIMM handling
 * A handful of other minor fixes

# gpg: Signature made Thu 07 May 2020 06:00:55 BST
# gpg:                using RSA key 75F46586AE61A66CC44E87DC6C38CACA20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>" [full]
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>" [full]
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>" [full]
# gpg:                 aka "David Gibson (kernel.org) <dwg@kernel.org>" [unknown]
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-5.1-20200507:
  target-ppc: fix rlwimi, rlwinm, rlwnm for Clang-9
  spapr_nvdimm: Tweak error messages
  spapr_nvdimm.c: make 'label-size' mandatory
  target/ppc: Add support for Radix partition-scoped translation
  target/ppc: Rework ppc_radix64_walk_tree() for partition-scoped translation
  target/ppc: Extend ppc_radix64_check_prot() with a 'partition_scoped' bool
  target/ppc: Introduce ppc_radix64_xlate() for Radix tree translation
  spapr: Don't allow unplug of NVLink2 devices
  target/ppc: Assert if HV mode is set when running under a pseries machine
  target/ppc: Introduce a relocation bool in ppc_radix64_handle_mmu_fault()
  target/ppc: Enforce that the root page directory size must be at least 5
  spapr: Drop CAS reboot flag
  spapr/cas: Separate CAS handling from rebuilding the FDT
  spapr: Simplify selection of radix/hash during CAS
  ppc/pnv: Add support for NMI interface
  ppc/spapr: tweak change system reset helper
  spapr: Don't check capabilities removed between CAS calls
  target/ppc: Improve syscall exception logging

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 103 insertions, 77 deletions

diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index c9cb6fa..a3b7a8d 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -27,6 +27,7 @@
 #include "sysemu/runstate.h"
 #include "sysemu/cpus.h"
 #include "sysemu/device_tree.h"
+#include "sysemu/hw_accel.h"
 #include "target/ppc/cpu.h"
 #include "qemu/log.h"
 #include "hw/ppc/fdt.h"
@@ -34,6 +35,7 @@
 #include "hw/ppc/pnv.h"
 #include "hw/ppc/pnv_core.h"
 #include "hw/loader.h"
+#include "hw/nmi.h"
 #include "exec/address-spaces.h"
 #include "qapi/visitor.h"
 #include "monitor/monitor.h"
@@ -1977,10 +1979,35 @@ static void pnv_machine_set_hb(Object *obj, bool value, Error **errp)
     }
 }
 
+static void pnv_cpu_do_nmi_on_cpu(CPUState *cs, run_on_cpu_data arg)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
+
+    cpu_synchronize_state(cs);
+    ppc_cpu_do_system_reset(cs);
+    /*
+     * SRR1[42:45] is set to 0100 which the ISA defines as implementation
+     * dependent. POWER processors use this for xscom triggered interrupts,
+     * which come from the BMC or NMI IPIs.
+     */
+    env->spr[SPR_SRR1] |= PPC_BIT(43);
+}
+
+static void pnv_nmi(NMIState *n, int cpu_index, Error **errp)
+{
+    CPUState *cs;
+
+    CPU_FOREACH(cs) {
+        async_run_on_cpu(cs, pnv_cpu_do_nmi_on_cpu, RUN_ON_CPU_NULL);
+    }
+}
+
 static void pnv_machine_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
     InterruptStatsProviderClass *ispc = INTERRUPT_STATS_PROVIDER_CLASS(oc);
+    NMIClass *nc = NMI_CLASS(oc);
 
     mc->desc = "IBM PowerNV (Non-Virtualized)";
     mc->init = pnv_init;
@@ -1997,6 +2024,7 @@ static void pnv_machine_class_init(ObjectClass *oc, void *data)
     mc->default_ram_size = INITRD_LOAD_ADDR + INITRD_MAX_SIZE;
     mc->default_ram_id = "pnv.ram";
     ispc->print_info = pnv_pic_print_info;
+    nc->nmi_monitor_handler = pnv_nmi;
 
     object_class_property_add_bool(oc, "hb-mode",
                                    pnv_machine_get_hb, pnv_machine_set_hb,
@@ -2060,6 +2088,7 @@ static const TypeInfo types[] = {
         .class_size    = sizeof(PnvMachineClass),
         .interfaces = (InterfaceInfo[]) {
             { TYPE_INTERRUPT_STATS_PROVIDER },
+            { TYPE_NMI },
             { },
         },
     },
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index fd5bfd1..c18eab0 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -96,7 +96,6 @@
  *
  * We load our kernel at 4M, leaving space for SLOF initial image
  */
-#define FDT_MAX_SIZE            0x100000
 #define RTAS_MAX_ADDR           0x80000000 /* RTAS must stay below that */
 #define FW_MAX_SIZE             0x400000
 #define FW_FILE_NAME            "slof.bin"
@@ -1580,9 +1579,7 @@ void spapr_setup_hpt(SpaprMachineState *spapr)
 {
     int hpt_shift;
 
-    if ((spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED)
-        || (spapr->cas_reboot
-            && !spapr_ovec_test(spapr->ov5_cas, OV5_HPT_RESIZE))) {
+    if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED) {
         hpt_shift = spapr_hpt_shift_for_ramsize(MACHINE(spapr)->maxram_size);
     } else {
         uint64_t current_ram_size;
@@ -1646,16 +1643,10 @@ static void spapr_machine_reset(MachineState *machine)
 
     qemu_devices_reset();
 
-    /*
-     * If this reset wasn't generated by CAS, we should reset our
-     * negotiated options and start from scratch
-     */
-    if (!spapr->cas_reboot) {
-        spapr_ovec_cleanup(spapr->ov5_cas);
-        spapr->ov5_cas = spapr_ovec_new();
+    spapr_ovec_cleanup(spapr->ov5_cas);
+    spapr->ov5_cas = spapr_ovec_new();
 
-        ppc_set_compat_all(spapr->max_compat_pvr, &error_fatal);
-    }
+    ppc_set_compat_all(spapr->max_compat_pvr, &error_fatal);
 
     /*
      * This is fixing some of the default configuration of the XIVE
@@ -1708,8 +1699,6 @@ static void spapr_machine_reset(MachineState *machine)
     spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT, 0, fdt_addr, 0);
     first_ppc_cpu->env.gpr[5] = 0;
 
-    spapr->cas_reboot = false;
-
     spapr->fwnmi_system_reset_addr = -1;
     spapr->fwnmi_machine_check_addr = -1;
     spapr->fwnmi_machine_check_interlock = -1;
@@ -2837,6 +2826,7 @@ static void spapr_machine_init(MachineState *machine)
     if ((!kvm_enabled() || kvmppc_has_cap_mmu_radix()) &&
         ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0,
                               spapr->max_compat_pvr)) {
+        spapr_ovec_set(spapr->ov5, OV5_MMU_RADIX_300);
         /* KVM and TCG always allow GTSE with radix... */
         spapr_ovec_set(spapr->ov5, OV5_MMU_RADIX_GTSE);
     }
@@ -3385,13 +3375,13 @@ static void spapr_machine_finalizefn(Object *obj)
 void spapr_do_system_reset_on_cpu(CPUState *cs, run_on_cpu_data arg)
 {
     SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUPPCState *env = &cpu->env;
 
     cpu_synchronize_state(cs);
     /* If FWNMI is inactive, addr will be -1, which will deliver to 0x100 */
     if (spapr->fwnmi_system_reset_addr != -1) {
         uint64_t rtas_addr, addr;
-        PowerPCCPU *cpu = POWERPC_CPU(cs);
-        CPUPPCState *env = &cpu->env;
 
         /* get rtas addr from fdt */
         rtas_addr = spapr_get_rtas_addr();
@@ -3405,7 +3395,10 @@ void spapr_do_system_reset_on_cpu(CPUState *cs, run_on_cpu_data arg)
         stq_be_phys(&address_space_memory, addr + sizeof(uint64_t), 0);
         env->gpr[3] = addr;
     }
-    ppc_cpu_do_system_reset(cs, spapr->fwnmi_system_reset_addr);
+    ppc_cpu_do_system_reset(cs);
+    if (spapr->fwnmi_system_reset_addr != -1) {
+        env->nip = spapr->fwnmi_system_reset_addr;
+    }
 }
 
 static void spapr_nmi(NMIState *n, int cpu_index, Error **errp)
diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index 0d50fc9..0f54988 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -1665,23 +1665,20 @@ static void spapr_handle_transient_dev_before_cas(SpaprMachineState *spapr)
     spapr_clear_pending_hotplug_events(spapr);
 }
 
-static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
-                                                  SpaprMachineState *spapr,
-                                                  target_ulong opcode,
-                                                  target_ulong *args)
+target_ulong do_client_architecture_support(PowerPCCPU *cpu,
+                                            SpaprMachineState *spapr,
+                                            target_ulong vec,
+                                            target_ulong fdt_bufsize)
 {
-    /* Working address in data buffer */
-    target_ulong addr = ppc64_phys_to_real(args[0]);
-    target_ulong fdt_buf = args[1];
-    target_ulong fdt_bufsize = args[2];
-    target_ulong ov_table;
+    target_ulong ov_table; /* Working address in data buffer */
     uint32_t cas_pvr;
-    SpaprOptionVector *ov1_guest, *ov5_guest, *ov5_cas_old;
+    SpaprOptionVector *ov1_guest, *ov5_guest;
     bool guest_radix;
     Error *local_err = NULL;
     bool raw_mode_supported = false;
     bool guest_xive;
     CPUState *cs;
+    void *fdt;
 
     /* CAS is supposed to be called early when only the boot vCPU is active. */
     CPU_FOREACH(cs) {
@@ -1694,7 +1691,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
         }
     }
 
-    cas_pvr = cas_check_pvr(spapr, cpu, &addr, &raw_mode_supported, &local_err);
+    cas_pvr = cas_check_pvr(spapr, cpu, &vec, &raw_mode_supported, &local_err);
     if (local_err) {
         error_report_err(local_err);
         return H_HARDWARE;
@@ -1717,7 +1714,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
     }
 
     /* For the future use: here @ov_table points to the first option vector */
-    ov_table = addr;
+    ov_table = vec;
 
     ov1_guest = spapr_ovec_parse_vector(ov_table, 1);
     if (!ov1_guest) {
@@ -1739,9 +1736,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
         exit(EXIT_FAILURE);
     }
 
-    /* The radix/hash bit in byte 24 requires special handling: */
     guest_radix = spapr_ovec_test(ov5_guest, OV5_MMU_RADIX_300);
-    spapr_ovec_clear(ov5_guest, OV5_MMU_RADIX_300);
 
     guest_xive = spapr_ovec_test(ov5_guest, OV5_XIVE_EXPLOIT);
 
@@ -1782,30 +1777,16 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
      * by LoPAPR 1.1, 14.5.4.8, which QEMU doesn't implement, we don't need
      * to worry about this for now.
      */
-    ov5_cas_old = spapr_ovec_clone(spapr->ov5_cas);
-
-    /* also clear the radix/hash bit from the current ov5_cas bits to
-     * be in sync with the newly ov5 bits. Else the radix bit will be
-     * seen as being removed and this will generate a reset loop
-     */
-    spapr_ovec_clear(ov5_cas_old, OV5_MMU_RADIX_300);
 
     /* full range of negotiated ov5 capabilities */
     spapr_ovec_intersect(spapr->ov5_cas, spapr->ov5, ov5_guest);
     spapr_ovec_cleanup(ov5_guest);
-    /* capabilities that have been added since CAS-generated guest reset.
-     * if capabilities have since been removed, generate another reset
-     */
-    spapr->cas_reboot = !spapr_ovec_subset(ov5_cas_old, spapr->ov5_cas);
-    spapr_ovec_cleanup(ov5_cas_old);
-    /* Now that processing is finished, set the radix/hash bit for the
-     * guest if it requested a valid mode; otherwise terminate the boot. */
+
     if (guest_radix) {
         if (kvm_enabled() && !kvmppc_has_cap_mmu_radix()) {
             error_report("Guest requested unavailable MMU mode (radix).");
             exit(EXIT_FAILURE);
         }
-        spapr_ovec_set(spapr->ov5_cas, OV5_MMU_RADIX_300);
     } else {
         if (kvm_enabled() && kvmppc_has_cap_mmu_radix()
             && !kvmppc_has_cap_mmu_hash_v3()) {
@@ -1838,44 +1819,57 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
 
     spapr_handle_transient_dev_before_cas(spapr);
 
-    if (!spapr->cas_reboot) {
-        void *fdt;
-        SpaprDeviceTreeUpdateHeader hdr = { .version_id = 1 };
+    /*
+     * If spapr_machine_reset() did not set up a HPT but one is necessary
+     * (because the guest isn't going to use radix) then set it up here.
+     */
+    if ((spapr->patb_entry & PATE1_GR) && !guest_radix) {
+        /* legacy hash or new hash: */
+        spapr_setup_hpt(spapr);
+    }
 
-        /* If spapr_machine_reset() did not set up a HPT but one is necessary
-         * (because the guest isn't going to use radix) then set it up here. */
-        if ((spapr->patb_entry & PATE1_GR) && !guest_radix) {
-            /* legacy hash or new hash: */
-            spapr_setup_hpt(spapr);
-        }
+    fdt = spapr_build_fdt(spapr, false, fdt_bufsize);
 
-        if (fdt_bufsize < sizeof(hdr)) {
-            error_report("SLOF provided insufficient CAS buffer "
-                         TARGET_FMT_lu " (min: %zu)", fdt_bufsize, sizeof(hdr));
-            exit(EXIT_FAILURE);
-        }
+    g_free(spapr->fdt_blob);
+    spapr->fdt_size = fdt_totalsize(fdt);
+    spapr->fdt_initial_size = spapr->fdt_size;
+    spapr->fdt_blob = fdt;
 
-        fdt_bufsize -= sizeof(hdr);
+    return H_SUCCESS;
+}
+
+static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
+                                                  SpaprMachineState *spapr,
+                                                  target_ulong opcode,
+                                                  target_ulong *args)
+{
+    target_ulong vec = ppc64_phys_to_real(args[0]);
+    target_ulong fdt_buf = args[1];
+    target_ulong fdt_bufsize = args[2];
+    target_ulong ret;
+    SpaprDeviceTreeUpdateHeader hdr = { .version_id = 1 };
 
-        fdt = spapr_build_fdt(spapr, false, fdt_bufsize);
-        _FDT((fdt_pack(fdt)));
+    if (fdt_bufsize < sizeof(hdr)) {
+        error_report("SLOF provided insufficient CAS buffer "
+                     TARGET_FMT_lu " (min: %zu)", fdt_bufsize, sizeof(hdr));
+        exit(EXIT_FAILURE);
+    }
 
-        cpu_physical_memory_write(fdt_buf, &hdr, sizeof(hdr));
-        cpu_physical_memory_write(fdt_buf + sizeof(hdr), fdt,
-                                  fdt_totalsize(fdt));
-        trace_spapr_cas_continue(fdt_totalsize(fdt) + sizeof(hdr));
+    fdt_bufsize -= sizeof(hdr);
 
-        g_free(spapr->fdt_blob);
-        spapr->fdt_size = fdt_totalsize(fdt);
+    ret = do_client_architecture_support(cpu, spapr, vec, fdt_bufsize);
+    if (ret == H_SUCCESS) {
+        _FDT((fdt_pack(spapr->fdt_blob)));
+        spapr->fdt_size = fdt_totalsize(spapr->fdt_blob);
         spapr->fdt_initial_size = spapr->fdt_size;
-        spapr->fdt_blob = fdt;
-    }
 
-    if (spapr->cas_reboot) {
-        qemu_system_reset_request(SHUTDOWN_CAUSE_SUBSYSTEM_RESET);
+        cpu_physical_memory_write(fdt_buf, &hdr, sizeof(hdr));
+        cpu_physical_memory_write(fdt_buf + sizeof(hdr), spapr->fdt_blob,
+                                  spapr->fdt_size);
+        trace_spapr_cas_continue(spapr->fdt_size + sizeof(hdr));
     }
 
-    return H_SUCCESS;
+    return ret;
 }
 
 static target_ulong h_home_node_associativity(PowerPCCPU *cpu,
diff --git a/hw/ppc/spapr_nvdimm.c b/hw/ppc/spapr_nvdimm.c
index 25be808..81410aa 100644
--- a/hw/ppc/spapr_nvdimm.c
+++ b/hw/ppc/spapr_nvdimm.c
@@ -37,9 +37,15 @@ void spapr_nvdimm_validate_opts(NVDIMMDevice *nvdimm, uint64_t size,
     QemuUUID uuid;
     int ret;
 
+    if (object_property_get_int(OBJECT(nvdimm), NVDIMM_LABEL_SIZE_PROP,
+                                &error_abort) == 0) {
+        error_setg(errp, "PAPR requires NVDIMM devices to have label-size set");
+        return;
+    }
+
     if (size % SPAPR_MINIMUM_SCM_BLOCK_SIZE) {
-        error_setg(errp, "NVDIMM memory size excluding the label area"
-                   " must be a multiple of %" PRIu64 "MB",
+        error_setg(errp, "PAPR requires NVDIMM memory size (excluding label)"
+                   " to be a multiple of %" PRIu64 "MB",
                    SPAPR_MINIMUM_SCM_BLOCK_SIZE / MiB);
         return;
     }
diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
index 55ca9de..61b84a3 100644
--- a/hw/ppc/spapr_pci.c
+++ b/hw/ppc/spapr_pci.c
@@ -1665,6 +1665,10 @@ static void spapr_pci_unplug_request(HotplugHandler *plug_handler,
             error_setg(errp, "PCI: Hot unplug of PCI bridges not supported");
             return;
         }
+        if (object_property_get_uint(OBJECT(pdev), "nvlink2-tgt", NULL)) {
+            error_setg(errp, "PCI: Cannot unplug NVLink2 devices");
+            return;
+        }
 
         /* ensure any other present functions are pending unplug */
         if (PCI_FUNC(pdev->devfn) == 0) {