Merge tag 'pull-ppc-20230626' of https://github.com/legoater/qemu int…

…o staging

ppc queue:

* New maintainers
* Nested implementation cleanups
* Various cleanups of the CPU implementation
* SMT support for pseries
* Improvements of the XIVE2 TIMA modeling
* Extra avocado tests for pseries

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmSZKF8ACgkQUaNDx8/7
# 7KGSiBAAlHC4S9J5ujzTIojaWY72d2ZinkC+WpBus9Wr91DqaUSUd/JbzDxQCvXh
# dBWEbcyQ+abb8M3OQ3fMq9TfD2/LhxxXb+uwHIJ+ylITBnsRVCQv/4/gi3EkpRid
# h4q3wYH8OYNfCQd/cWYXNgCSNj1nS9sRrEKFXaB0JeQWHzHxriJS/SoIhilqvUru
# LFEytWNb3bxRkEkt8oAetOa9+DNLowUQ9IdzswqGcib09po3b1k4+ThfcvzU9nAc
# ek31/h1W6cJbOJcgRO2dhWUZYp7cfmcnOa02E84tGFvvY/kYbjzPZZnoniSXD4uf
# YWFCoB3VxUoZ/YKCT/pDKHVdXmLLrfckNbo9vQNEcwmjr8m0Q3d1ewD5O9oNRpgN
# H0QMENfsdojztosOm3KPQ20aqNf1R7rQegYTiWf3B2fKZ6PIqnn3tBPxaEDkH7NC
# GTAKnBhF48lcHSF/4XOfGdmqhGgPRWX/Tv0wia7RY/A4NEfiIImIu+nYSGNBbu3y
# 7xlmtcumTlsRityOZnYI3bN5ubv++XPwU5NIJPACqvAbhif2rf1vQ9rMkkK785GL
# ciJ/5f6zXsLU7DfWP+qbTBizchQgigXnRZEEc7Seo6Bwtru22oxug0qQZ5QCgyXl
# Fg5Xuoq/6T4JC75pvxh1BjVlZc3Okzbfmsj+aZNrXO581HVJ2JI=
# =XLtJ
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 26 Jun 2023 07:55:43 AM CEST
# gpg:                using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@kaod.org>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: A0F6 6548 F048 95EB FE6B  0B60 51A3 43C7 CFFB ECA1

* tag 'pull-ppc-20230626' of https://github.com/legoater/qemu: (30 commits)
  tests/avocado: ppc test VOF bios Linux boot
  pnv/xive2: Check TIMA special ops against a dedicated array for P10
  pnv/xive2: Add a get_config() method on the presenter class
  tests/avocado: Add ppc64 pseries multiprocessor boot tests
  tests/avocado: boot ppc64 pseries to Linux VFS mount
  spapr: TCG allow up to 8-thread SMT on POWER8 and newer CPUs
  hw/ppc/spapr: Test whether TCG is enabled with tcg_enabled()
  target/ppc: Add msgsnd/p and DPDES SMT support
  target/ppc: Add support for SMT CTRL register
  target/ppc: Add initial flags and helpers for SMT support
  target/ppc: Fix sc instruction handling of LEV field
  target/ppc: Better CTRL SPR implementation
  target/ppc: Add ISA v3.1 LEV indication in SRR1 for system call interrupts
  target/ppc: Implement HEIR SPR
  target/ppc: Add SRR1 prefix indication to interrupt handlers
  target/ppc: Change partition-scope translate interface
  target/ppc: Fix instruction loading endianness in alignment interrupt
  ppc/spapr: Move spapr nested HV to a new file
  ppc/spapr: load and store l2 state with helper functions
  ppc/spapr: Add a nested state struct
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

MAINTAINERS

@@ -302,6 +302,7 @@ M: Daniel Henrique Barboza <danielhb413@gmail.com>
 R: Cédric Le Goater <clg@kaod.org>
 R: David Gibson <david@gibson.dropbear.id.au>
 R: Greg Kurz <groug@kaod.org>
+R: Nicholas Piggin <npiggin@gmail.com>
 L: qemu-ppc@nongnu.org
 S: Odd Fixes
 F: target/ppc/
@@ -1451,6 +1452,8 @@ F: tests/avocado/ppc_pseries.py
 
 PowerNV (Non-Virtualized)
 M: Cédric Le Goater <clg@kaod.org>
+R: Frédéric Barrat <fbarrat@linux.ibm.com>
+R: Nicholas Piggin <npiggin@gmail.com>
 L: qemu-ppc@nongnu.org
 S: Odd Fixes
 F: docs/system/ppc/powernv.rst
@@ -2445,6 +2448,7 @@ T: git https://github.com/philmd/qemu.git fw_cfg-next
 
 XIVE
 M: Cédric Le Goater <clg@kaod.org>
+R: Frédéric Barrat <fbarrat@linux.ibm.com>
 L: qemu-ppc@nongnu.org
 S: Odd Fixes
 F: hw/*/*xive*

hw/intc/pnv_xive.c

@@ -479,6 +479,16 @@ static int pnv_xive_match_nvt(XivePresenter *xptr, uint8_t format,
     return count;
 }
 
+static uint32_t pnv_xive_presenter_get_config(XivePresenter *xptr)
+{
+    uint32_t cfg = 0;
+
+    /* TIMA GEN1 is all P9 knows */
+    cfg |= XIVE_PRESENTER_GEN1_TIMA_OS;
+
+    return cfg;
+}
+
 static uint8_t pnv_xive_get_block_id(XiveRouter *xrtr)
 {
     return pnv_xive_block_id(PNV_XIVE(xrtr));
@@ -1991,6 +2001,7 @@ static void pnv_xive_class_init(ObjectClass *klass, void *data)
 
     xnc->notify = pnv_xive_notify;
     xpc->match_nvt  = pnv_xive_match_nvt;
+    xpc->get_config = pnv_xive_presenter_get_config;
 };
 
 static const TypeInfo pnv_xive_info = {

hw/intc/pnv_xive2.c

@@ -501,6 +501,17 @@ static int pnv_xive2_match_nvt(XivePresenter *xptr, uint8_t format,
     return count;
 }
 
+static uint32_t pnv_xive2_presenter_get_config(XivePresenter *xptr)
+{
+    PnvXive2 *xive = PNV_XIVE2(xptr);
+    uint32_t cfg = 0;
+
+    if (xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_GEN1_TIMA_OS) {
+        cfg |= XIVE_PRESENTER_GEN1_TIMA_OS;
+    }
+    return cfg;
+}
+
 static uint8_t pnv_xive2_get_block_id(Xive2Router *xrtr)
 {
     return pnv_xive2_block_id(PNV_XIVE2(xrtr));
@@ -1645,36 +1656,14 @@ static const MemoryRegionOps pnv_xive2_ic_tm_indirect_ops = {
 /*
  * TIMA ops
  */
-
-/*
- * Special TIMA offsets to handle accesses in a POWER10 way.
- *
- * Only the CAM line updates done by the hypervisor should be handled
- * specifically.
- */
-#define HV_PAGE_OFFSET         (XIVE_TM_HV_PAGE << TM_SHIFT)
-#define HV_PUSH_OS_CTX_OFFSET  (HV_PAGE_OFFSET | (TM_QW1_OS + TM_WORD2))
-#define HV_PULL_OS_CTX_OFFSET  (HV_PAGE_OFFSET | TM_SPC_PULL_OS_CTX)
-
 static void pnv_xive2_tm_write(void *opaque, hwaddr offset,
                                uint64_t value, unsigned size)
 {
     PowerPCCPU *cpu = POWERPC_CPU(current_cpu);
     PnvXive2 *xive = pnv_xive2_tm_get_xive(cpu);
     XiveTCTX *tctx = XIVE_TCTX(pnv_cpu_state(cpu)->intc);
     XivePresenter *xptr = XIVE_PRESENTER(xive);
-    bool gen1_tima_os =
-        xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_GEN1_TIMA_OS;
-
-    offset &= TM_ADDRESS_MASK;
-
-    /* TODO: should we switch the TM ops table instead ? */
-    if (!gen1_tima_os && offset == HV_PUSH_OS_CTX_OFFSET) {
-        xive2_tm_push_os_ctx(xptr, tctx, offset, value, size);
-        return;
-    }
 
-    /* Other TM ops are the same as XIVE1 */
     xive_tctx_tm_write(xptr, tctx, offset, value, size);
 }
 
@@ -1684,17 +1673,7 @@ static uint64_t pnv_xive2_tm_read(void *opaque, hwaddr offset, unsigned size)
     PnvXive2 *xive = pnv_xive2_tm_get_xive(cpu);
     XiveTCTX *tctx = XIVE_TCTX(pnv_cpu_state(cpu)->intc);
     XivePresenter *xptr = XIVE_PRESENTER(xive);
-    bool gen1_tima_os =
-        xive->cq_regs[CQ_XIVE_CFG >> 3] & CQ_XIVE_CFG_GEN1_TIMA_OS;
-
-    offset &= TM_ADDRESS_MASK;
-
-    /* TODO: should we switch the TM ops table instead ? */
-    if (!gen1_tima_os && offset == HV_PULL_OS_CTX_OFFSET) {
-        return xive2_tm_pull_os_ctx(xptr, tctx, offset, size);
-    }
 
-    /* Other TM ops are the same as XIVE1 */
     return xive_tctx_tm_read(xptr, tctx, offset, size);
 }
 
@@ -1987,6 +1966,7 @@ static void pnv_xive2_class_init(ObjectClass *klass, void *data)
     xnc->notify    = pnv_xive2_notify;
 
     xpc->match_nvt  = pnv_xive2_match_nvt;
+    xpc->get_config = pnv_xive2_presenter_get_config;
 };
 
 static const TypeInfo pnv_xive2_info = {

hw/intc/spapr_xive.c

@@ -475,6 +475,21 @@ static int spapr_xive_match_nvt(XivePresenter *xptr, uint8_t format,
     return count;
 }
 
+static uint32_t spapr_xive_presenter_get_config(XivePresenter *xptr)
+{
+    uint32_t cfg = 0;
+
+    /*
+     * Let's claim GEN1 TIMA format. If running with KVM on P10, the
+     * correct answer is deep in the hardware and not accessible to
+     * us.  But it shouldn't matter as it only affects the presenter
+     * as seen by a guest OS.
+     */
+    cfg |= XIVE_PRESENTER_GEN1_TIMA_OS;
+
+    return cfg;
+}
+
 static uint8_t spapr_xive_get_block_id(XiveRouter *xrtr)
 {
     return SPAPR_XIVE_BLOCK_ID;
@@ -832,6 +847,7 @@ static void spapr_xive_class_init(ObjectClass *klass, void *data)
     sicc->post_load = spapr_xive_post_load;
 
     xpc->match_nvt  = spapr_xive_match_nvt;
+    xpc->get_config = spapr_xive_presenter_get_config;
     xpc->in_kernel  = spapr_xive_in_kernel_xptr;
 }
 

hw/intc/xive.c

@@ -20,6 +20,7 @@
 #include "monitor/monitor.h"
 #include "hw/irq.h"
 #include "hw/ppc/xive.h"
+#include "hw/ppc/xive2.h"
 #include "hw/ppc/xive_regs.h"
 #include "trace.h"
 
@@ -461,6 +462,13 @@ static void xive_tm_push_os_ctx(XivePresenter *xptr, XiveTCTX *tctx,
     }
 }
 
+static uint32_t xive_presenter_get_config(XivePresenter *xptr)
+{
+    XivePresenterClass *xpc = XIVE_PRESENTER_GET_CLASS(xptr);
+
+    return xpc->get_config(xptr);
+}
+
 /*
  * Define a mapping of "special" operations depending on the TIMA page
  * offset and the size of the operation.
@@ -497,14 +505,47 @@ static const XiveTmOp xive_tm_operations[] = {
     { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX,  8, NULL, xive_tm_pull_pool_ctx },
 };
 
-static const XiveTmOp *xive_tm_find_op(hwaddr offset, unsigned size, bool write)
+static const XiveTmOp xive2_tm_operations[] = {
+    /*
+     * MMIOs below 2K : raw values and special operations without side
+     * effects
+     */
+    { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR,   1, xive_tm_set_os_cppr, NULL },
+    { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2,  4, xive2_tm_push_os_ctx, NULL },
+    { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive_tm_set_hv_cppr, NULL },
+    { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, xive_tm_vt_push, NULL },
+    { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, NULL, xive_tm_vt_poll },
+
+    /* MMIOs above 2K : special operations with side effects */
+    { XIVE_TM_OS_PAGE, TM_SPC_ACK_OS_REG,     2, NULL, xive_tm_ack_os_reg },
+    { XIVE_TM_OS_PAGE, TM_SPC_SET_OS_PENDING, 1, xive_tm_set_os_pending, NULL },
+    { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX,    4, NULL, xive2_tm_pull_os_ctx },
+    { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX,    8, NULL, xive2_tm_pull_os_ctx },
+    { XIVE_TM_HV_PAGE, TM_SPC_ACK_HV_REG,     2, NULL, xive_tm_ack_hv_reg },
+    { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX,  4, NULL, xive_tm_pull_pool_ctx },
+    { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX,  8, NULL, xive_tm_pull_pool_ctx },
+};
+
+static const XiveTmOp *xive_tm_find_op(XivePresenter *xptr, hwaddr offset,
+                                       unsigned size, bool write)
 {
     uint8_t page_offset = (offset >> TM_SHIFT) & 0x3;
     uint32_t op_offset = offset & TM_ADDRESS_MASK;
-    int i;
+    const XiveTmOp *tm_ops;
+    int i, tm_ops_count;
+    uint32_t cfg;
+
+    cfg = xive_presenter_get_config(xptr);
+    if (cfg & XIVE_PRESENTER_GEN1_TIMA_OS) {
+        tm_ops = xive_tm_operations;
+        tm_ops_count = ARRAY_SIZE(xive_tm_operations);
+    } else {
+        tm_ops = xive2_tm_operations;
+        tm_ops_count = ARRAY_SIZE(xive2_tm_operations);
+    }
 
-    for (i = 0; i < ARRAY_SIZE(xive_tm_operations); i++) {
-        const XiveTmOp *xto = &xive_tm_operations[i];
+    for (i = 0; i < tm_ops_count; i++) {
+        const XiveTmOp *xto = &tm_ops[i];
 
         /* Accesses done from a more privileged TIMA page is allowed */
         if (xto->page_offset >= page_offset &&
@@ -535,7 +576,7 @@ void xive_tctx_tm_write(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
      * First, check for special operations in the 2K region
      */
     if (offset & TM_SPECIAL_OP) {
-        xto = xive_tm_find_op(offset, size, true);
+        xto = xive_tm_find_op(tctx->xptr, offset, size, true);
         if (!xto) {
             qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid write access at TIMA "
                           "@%"HWADDR_PRIx"\n", offset);
@@ -548,7 +589,7 @@ void xive_tctx_tm_write(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
     /*
      * Then, for special operations in the region below 2K.
      */
-    xto = xive_tm_find_op(offset, size, true);
+    xto = xive_tm_find_op(tctx->xptr, offset, size, true);
     if (xto) {
         xto->write_handler(xptr, tctx, offset, value, size);
         return;
@@ -574,7 +615,7 @@ uint64_t xive_tctx_tm_read(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
      * First, check for special operations in the 2K region
      */
     if (offset & TM_SPECIAL_OP) {
-        xto = xive_tm_find_op(offset, size, false);
+        xto = xive_tm_find_op(tctx->xptr, offset, size, false);
         if (!xto) {
             qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid read access to TIMA"
                           "@%"HWADDR_PRIx"\n", offset);
@@ -587,7 +628,7 @@ uint64_t xive_tctx_tm_read(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset,
     /*
      * Then, for special operations in the region below 2K.
      */
-    xto = xive_tm_find_op(offset, size, false);
+    xto = xive_tm_find_op(tctx->xptr, offset, size, false);
     if (xto) {
         ret = xto->read_handler(xptr, tctx, offset, size);
         goto out;

hw/pci-host/pnv_phb4.c

@@ -133,13 +133,13 @@ static void pnv_phb4_rc_config_write(PnvPHB4 *phb, unsigned off,
     PCIDevice *pdev;
 
     if (size != 4) {
-        phb_error(phb, "rc_config_write invalid size %d\n", size);
+        phb_error(phb, "rc_config_write invalid size %d", size);
         return;
     }
 
     pdev = pci_find_device(pci->bus, 0, 0);
     if (!pdev) {
-        phb_error(phb, "rc_config_write device not found\n");
+        phb_error(phb, "rc_config_write device not found");
         return;
     }
 
@@ -155,13 +155,13 @@ static uint64_t pnv_phb4_rc_config_read(PnvPHB4 *phb, unsigned off,
     uint64_t val;
 
     if (size != 4) {
-        phb_error(phb, "rc_config_read invalid size %d\n", size);
+        phb_error(phb, "rc_config_read invalid size %d", size);
         return ~0ull;
     }
 
     pdev = pci_find_device(pci->bus, 0, 0);
     if (!pdev) {
-        phb_error(phb, "rc_config_read device not found\n");
+        phb_error(phb, "rc_config_read device not found");
         return ~0ull;
     }
 
@@ -1039,19 +1039,19 @@ static void pnv_pec_stk_nest_xscom_write(void *opaque, hwaddr addr,
         if (phb->nest_regs[PEC_NEST_STK_BAR_EN] &
             (PEC_NEST_STK_BAR_EN_MMIO0 |
              PEC_NEST_STK_BAR_EN_MMIO1)) {
-            phb_pec_error(pec, "Changing enabled BAR unsupported\n");
+            phb_pec_error(pec, "Changing enabled BAR unsupported");
         }
         phb->nest_regs[reg] = val & 0xffffffffff000000ull;
         break;
     case PEC_NEST_STK_PHB_REGS_BAR:
         if (phb->nest_regs[PEC_NEST_STK_BAR_EN] & PEC_NEST_STK_BAR_EN_PHB) {
-            phb_pec_error(pec, "Changing enabled BAR unsupported\n");
+            phb_pec_error(pec, "Changing enabled BAR unsupported");
         }
         phb->nest_regs[reg] = val & 0xffffffffffc00000ull;
         break;
     case PEC_NEST_STK_INT_BAR:
         if (phb->nest_regs[PEC_NEST_STK_BAR_EN] & PEC_NEST_STK_BAR_EN_INT) {
-            phb_pec_error(pec, "Changing enabled BAR unsupported\n");
+            phb_pec_error(pec, "Changing enabled BAR unsupported");
         }
         phb->nest_regs[reg] = val & 0xfffffff000000000ull;
         break;

hw/ppc/meson.build

@@ -15,6 +15,7 @@ ppc_ss.add(when: 'CONFIG_PSERIES', if_true: files(
   'spapr_vio.c',
   'spapr_events.c',
   'spapr_hcall.c',
+  'spapr_nested.c',
   'spapr_iommu.c',
   'spapr_rtas.c',
   'spapr_pci.c',

hw/ppc/pnv.c

@@ -799,7 +799,8 @@ static void pnv_init(MachineState *machine)
     DeviceState *dev;
 
     if (kvm_enabled()) {
-        error_report("The powernv machine does not work with KVM acceleration");
+        error_report("machine %s does not support the KVM accelerator",
+                     mc->name);
         exit(EXIT_FAILURE);
     }
 

hw/ppc/ppc.c

@@ -1436,6 +1436,12 @@ int ppc_cpu_pir(PowerPCCPU *cpu)
     return env->spr_cb[SPR_PIR].default_value;
 }
 
+int ppc_cpu_tir(PowerPCCPU *cpu)
+{
+    CPUPPCState *env = &cpu->env;
+    return env->spr_cb[SPR_TIR].default_value;
+}
+
 PowerPCCPU *ppc_get_vcpu_by_pir(int pir)
 {
     CPUState *cs;

hw/ppc/ppc440_bamboo.c

@@ -19,7 +19,6 @@
 #include "hw/pci/pci.h"
 #include "hw/boards.h"
 #include "sysemu/kvm.h"
-#include "kvm_ppc.h"
 #include "sysemu/device_tree.h"
 #include "hw/loader.h"
 #include "elf.h"
@@ -97,16 +96,6 @@ static int bamboo_load_device_tree(MachineState *machine,
         fprintf(stderr, "couldn't set /chosen/bootargs\n");
     }
 
-    /*
-     * Copy data from the host device tree into the guest. Since the guest can
-     * directly access the timebase without host involvement, we must expose
-     * the correct frequencies.
-     */
-    if (kvm_enabled()) {
-        tb_freq = kvmppc_get_tbfreq();
-        clock_freq = kvmppc_get_clockfreq();
-    }
-
     qemu_fdt_setprop_cell(fdt, "/cpus/cpu@0", "clock-frequency",
                           clock_freq);
     qemu_fdt_setprop_cell(fdt, "/cpus/cpu@0", "timebase-frequency",
@@ -175,6 +164,12 @@ static void bamboo_init(MachineState *machine)
     int success;
     int i;
 
+    if (kvm_enabled()) {
+        error_report("machine %s does not support the KVM accelerator",
+                     MACHINE_GET_CLASS(machine)->name);
+        exit(EXIT_FAILURE);
+    }
+
     cpu = POWERPC_CPU(cpu_create(machine->cpu_type));
     env = &cpu->env;