Merge tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu into staging

virtio: features,fixes

A bunch of improvements:
- vhost dirty log is now only scanned once, not once per device
- virtio and vhost now support VIRTIO_F_NOTIFICATION_DATA
- cxl gained DCD emulation support
- pvpanic gained shutdown support
- beginning of patchset for Generic Port Affinity Structure
- s3 support
- friendlier error messages when boot fails on some illegal configs
- for vhost-user, VHOST_USER_SET_LOG_BASE is now only sent once
- part of vhost-user support for any POSIX system -
  not yet enabled due to qtest failures
- sr-iov VF setup code has been reworked significantly
- new tests, particularly for risc-v ACPI
- bugfixes

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmaF068PHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp+DMIAMC//mBXIZlPprfhb5cuZklxYi31Acgu5TUr
# njqjCkN+mFhXXZuc3B67xmrQ066IEPtsbzCjSnzuU41YK4tjvO1g+LgYJBv41G16
# va2k8vFM5pdvRA+UC9li1CCIPxiEcszxOdzZemj3szWLVLLUmwsc5OZLWWeFA5m8
# vXrrT9miODUz3z8/Xn/TVpxnmD6glKYIRK/IJRzzC4Qqqwb5H3ji/BJV27cDUtdC
# w6ns5RYIj5j4uAiG8wQNDggA1bMsTxFxThRDUwxlxaIwAcexrf1oRnxGRePA7PVG
# BXrt5yodrZYR2sR6svmOOIF3wPMUDKdlAItTcEgYyxaVo5rAdpc=
# =p9h4
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 03 Jul 2024 03:41:51 PM PDT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [undefined]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [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: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (85 commits)
  hw/pci: Replace -1 with UINT32_MAX for romsize
  pcie_sriov: Register VFs after migration
  pcie_sriov: Remove num_vfs from PCIESriovPF
  pcie_sriov: Release VFs failed to realize
  pcie_sriov: Reuse SR-IOV VF device instances
  pcie_sriov: Ensure VF function number does not overflow
  pcie_sriov: Do not manually unrealize
  hw/ppc/spapr_pci: Do not reject VFs created after a PF
  hw/ppc/spapr_pci: Do not create DT for disabled PCI device
  hw/pci: Rename has_power to enabled
  virtio-iommu: Clear IOMMUDevice when VFIO device is unplugged
  virtio: remove virtio_tswap16s() call in vring_packed_event_read()
  hw/cxl/events: Mark cxl-add-dynamic-capacity and cxl-release-dynamic-capcity unstable
  hw/cxl/events: Improve QMP interfaces and documentation for add/release dynamic capacity.
  tests/data/acpi/rebuild-expected-aml.sh: Add RISC-V
  pc-bios/meson.build: Add support for RISC-V in unpack_edk2_blobs
  meson.build: Add RISC-V to the edk2-target list
  tests/data/acpi/virt: Move ARM64 ACPI tables under aarch64/${machine} path
  tests/data/acpi: Move x86 ACPI tables under x86/${machine} path
  tests/qtest/bios-tables-test.c: Set "arch" for x86 tests
  ...

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

6 files changed, 31 insertions, 18 deletions

diff --git a/hw/i386/e820_memory_layout.c b/hw/i386/e820_memory_layout.c
index 06970ac..3e848fb 100644
--- a/hw/i386/e820_memory_layout.c
+++ b/hw/i386/e820_memory_layout.c
@@ -11,22 +11,29 @@
 #include "e820_memory_layout.h"
 
 static size_t e820_entries;
-struct e820_entry *e820_table;
+static struct e820_entry *e820_table;
+static gboolean e820_done;
 
-int e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
+void e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
 {
+    assert(!e820_done);
+
     /* new "etc/e820" file -- include ram and reserved entries */
     e820_table = g_renew(struct e820_entry, e820_table, e820_entries + 1);
     e820_table[e820_entries].address = cpu_to_le64(address);
     e820_table[e820_entries].length = cpu_to_le64(length);
     e820_table[e820_entries].type = cpu_to_le32(type);
     e820_entries++;
-
-    return e820_entries;
 }
 
-int e820_get_num_entries(void)
+int e820_get_table(struct e820_entry **table)
 {
+    e820_done = true;
+
+    if (table) {
+        *table = e820_table;
+    }
+
     return e820_entries;
 }
 
diff --git a/hw/i386/e820_memory_layout.h b/hw/i386/e820_memory_layout.h
index 7c239aa..b50acfa 100644
--- a/hw/i386/e820_memory_layout.h
+++ b/hw/i386/e820_memory_layout.h
@@ -22,13 +22,9 @@ struct e820_entry {
     uint32_t type;
 } QEMU_PACKED __attribute((__aligned__(4)));
 
-extern struct e820_entry *e820_table;
-
-int e820_add_entry(uint64_t address, uint64_t length, uint32_t type);
-int e820_get_num_entries(void);
+void e820_add_entry(uint64_t address, uint64_t length, uint32_t type);
 bool e820_get_entry(int index, uint32_t type,
                     uint64_t *address, uint64_t *length);
-
-
+int e820_get_table(struct e820_entry **table);
 
 #endif
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index 7c43c32..0e44946 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -48,6 +48,15 @@ const char *fw_cfg_arch_key_name(uint16_t key)
     return NULL;
 }
 
+/* Add etc/e820 late, once all regions should be present */
+void fw_cfg_add_e820(FWCfgState *fw_cfg)
+{
+    struct e820_entry *table;
+    int nr_e820 = e820_get_table(&table);
+
+    fw_cfg_add_file(fw_cfg, "etc/e820", table, nr_e820 * sizeof(*table));
+}
+
 void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
                          SmbiosEntryPointType ep_type)
 {
@@ -60,6 +69,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
     PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
     MachineClass *mc = MACHINE_GET_CLASS(pcms);
     X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
+    int nr_e820;
 
     if (pcmc->smbios_defaults) {
         /* These values are guest ABI, do not change */
@@ -78,8 +88,9 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
     }
 
     /* build the array of physical mem area from e820 table */
-    mem_array = g_malloc0(sizeof(*mem_array) * e820_get_num_entries());
-    for (i = 0, array_count = 0; i < e820_get_num_entries(); i++) {
+    nr_e820 = e820_get_table(NULL);
+    mem_array = g_malloc0(sizeof(*mem_array) * nr_e820);
+    for (i = 0, array_count = 0; i < nr_e820; i++) {
         uint64_t addr, len;
 
         if (e820_get_entry(i, E820_RAM, &addr, &len)) {
@@ -138,9 +149,6 @@ FWCfgState *fw_cfg_arch_create(MachineState *ms,
 #endif
     fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, 1);
 
-    fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,
-                    sizeof(struct e820_entry) * e820_get_num_entries());
-
     fw_cfg_add_bytes(fw_cfg, FW_CFG_HPET, &hpet_cfg, sizeof(hpet_cfg));
     /* allocate memory for the NUMA channel: one (64bit) word for the number
      * of nodes, one word for each VCPU->node and one word for each node to
diff --git a/hw/i386/fw_cfg.h b/hw/i386/fw_cfg.h
index 92e310f..e560fd7 100644
--- a/hw/i386/fw_cfg.h
+++ b/hw/i386/fw_cfg.h
@@ -27,5 +27,6 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
                          SmbiosEntryPointType ep_type);
 void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg);
 void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg);
+void fw_cfg_add_e820(FWCfgState *fw_cfg);
 
 #endif
diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c
index fec63ca..40edcee 100644
--- a/hw/i386/microvm.c
+++ b/hw/i386/microvm.c
@@ -324,8 +324,6 @@ static void microvm_memory_init(MicrovmMachineState *mms)
     fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, machine->smp.max_cpus);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)machine->ram_size);
     fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, 1);
-    fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,
-                    sizeof(struct e820_entry) * e820_get_num_entries());
 
     rom_set_fw(fw_cfg);
 
@@ -586,9 +584,11 @@ static void microvm_machine_done(Notifier *notifier, void *data)
 {
     MicrovmMachineState *mms = container_of(notifier, MicrovmMachineState,
                                             machine_done);
+    X86MachineState *x86ms = X86_MACHINE(mms);
 
     acpi_setup_microvm(mms);
     dt_setup_microvm(mms);
+    fw_cfg_add_e820(x86ms->fw_cfg);
 }
 
 static void microvm_powerdown_req(Notifier *notifier, void *data)
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 7741506..d2c29fb 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -625,6 +625,7 @@ void pc_machine_done(Notifier *notifier, void *data)
     acpi_setup();
     if (x86ms->fw_cfg) {
         fw_cfg_build_smbios(pcms, x86ms->fw_cfg, pcms->smbios_entry_point_type);
+        fw_cfg_add_e820(x86ms->fw_cfg);
         fw_cfg_build_feature_control(MACHINE(pcms), x86ms->fw_cfg);
         /* update FW_CFG_NB_CPUS to account for -device added CPUs */
         fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus);