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

virtio,pc,pci: features, cleanups, fixes

vhost-user support without ioeventfd
word replacements in vhost user spec
shpc improvements

cleanups, fixes all over the place

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmQBO8QPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRpMUMH/3/FVp4qaF4CDwCHn7xWFRJpOREIhX/iWfUu
# lGkwxnB7Lfyqdg7i4CAfgMf2emWKZchEE2DamfCo5bIX0IgRU3DWcOdR9ePvJ29J
# cKwIYpxZcB4RYSoWL5OUakQLCT3JOu4XWaXeVjyHABjQhf3lGpwN4KmIOBGOy/N6
# 0YHOQScW2eW62wIOwhAEuYQceMt6KU32Uw3tLnMbJliiBf3a/hPctVNM9TFY9pcd
# UYHGfBx/zD45owf1lTVEQFDg0eqPZKWW29g5haiOd5oAyXHHolzu+bt3bU7lH46b
# f7iP12LqDudyrgoF5YWv3NJ4HaGm5V3kPqNqLLF/mjF7alxG+N8=
# =hN3h
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 03 Mar 2023 00:13:56 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# 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: (53 commits)
  tests/data/acpi/virt: drop (most) duplicate files.
  hw/cxl/mailbox: Use new UUID network order define for cel_uuid
  qemu/uuid: Add UUID static initializer
  qemu/bswap: Add const_le64()
  tests: acpi: Update q35/DSDT.cxl for removed duplicate UID
  hw/i386/acpi: Drop duplicate _UID entry for CXL root bridge
  tests/acpi: Allow update of q35/DSDT.cxl
  hw/cxl: Add CXL_CAPACITY_MULTIPLIER definition
  hw/cxl: set cxl-type3 device type to PCI_CLASS_MEMORY_CXL
  hw/pci-bridge/cxl_downstream: Fix type naming mismatch
  hw/mem/cxl_type3: Improve error handling in realize()
  MAINTAINERS: Add Fan Ni as Compute eXpress Link QEMU reviewer
  intel-iommu: send UNMAP notifications for domain or global inv desc
  smmu: switch to use memory_region_unmap_iommu_notifier_range()
  memory: introduce memory_region_unmap_iommu_notifier_range()
  intel-iommu: fail DEVIOTLB_UNMAP without dt mode
  intel-iommu: fail MAP notifier without caching mode
  memory: Optimize replay of guest mapping
  chardev/char-socket: set s->listener = NULL in char_socket_finalize
  hw/pci: Trace IRQ routing on PCI topology
  ...

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

7 files changed, 65 insertions, 114 deletions

diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index d27921f..b19fb42 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -1514,7 +1514,6 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
                 aml_append(pkg, aml_eisaid("PNP0A03"));
                 aml_append(dev, aml_name_decl("_CID", pkg));
                 aml_append(dev, aml_name_decl("_ADR", aml_int(0)));
-                aml_append(dev, aml_name_decl("_UID", aml_int(bus_num)));
                 build_cxl_osc_method(dev);
             } else if (pci_bus_is_express(bus)) {
                 aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A08")));
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 98a5c30..faade7d 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -1530,13 +1530,17 @@ static int vtd_sync_shadow_page_table_range(VTDAddressSpace *vtd_as,
     return vtd_page_walk(s, ce, addr, addr + size, &info, vtd_as->pasid);
 }
 
-static int vtd_sync_shadow_page_table(VTDAddressSpace *vtd_as)
+static int vtd_address_space_sync(VTDAddressSpace *vtd_as)
 {
     int ret;
     VTDContextEntry ce;
     IOMMUNotifier *n;
 
-    if (!(vtd_as->iommu.iommu_notify_flags & IOMMU_NOTIFIER_IOTLB_EVENTS)) {
+    /* If no MAP notifier registered, we simply invalidate all the cache */
+    if (!vtd_as_has_map_notifier(vtd_as)) {
+        IOMMU_NOTIFIER_FOREACH(n, &vtd_as->iommu) {
+            memory_region_unmap_iommu_notifier_range(n);
+        }
         return 0;
     }
 
@@ -2000,7 +2004,7 @@ static void vtd_iommu_replay_all(IntelIOMMUState *s)
     VTDAddressSpace *vtd_as;
 
     QLIST_FOREACH(vtd_as, &s->vtd_as_with_notifiers, next) {
-        vtd_sync_shadow_page_table(vtd_as);
+        vtd_address_space_sync(vtd_as);
     }
 }
 
@@ -2082,7 +2086,7 @@ static void vtd_context_device_invalidate(IntelIOMMUState *s,
              * framework will skip MAP notifications if that
              * happened.
              */
-            vtd_sync_shadow_page_table(vtd_as);
+            vtd_address_space_sync(vtd_as);
         }
     }
 }
@@ -2140,7 +2144,7 @@ static void vtd_iotlb_domain_invalidate(IntelIOMMUState *s, uint16_t domain_id)
         if (!vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus),
                                       vtd_as->devfn, &ce) &&
             domain_id == vtd_get_domain_id(s, &ce, vtd_as->pasid)) {
-            vtd_sync_shadow_page_table(vtd_as);
+            vtd_address_space_sync(vtd_as);
         }
     }
 }
@@ -3179,6 +3183,7 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
 {
     VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
     IntelIOMMUState *s = vtd_as->iommu_state;
+    X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s);
 
     /* TODO: add support for VFIO and vhost users */
     if (s->snoop_control) {
@@ -3186,6 +3191,20 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
                          "Snoop Control with vhost or VFIO is not supported");
         return -ENOTSUP;
     }
+    if (!s->caching_mode && (new & IOMMU_NOTIFIER_MAP)) {
+        error_setg_errno(errp, ENOTSUP,
+                         "device %02x.%02x.%x requires caching mode",
+                         pci_bus_num(vtd_as->bus), PCI_SLOT(vtd_as->devfn),
+                         PCI_FUNC(vtd_as->devfn));
+        return -ENOTSUP;
+    }
+    if (!x86_iommu->dt_supported && (new & IOMMU_NOTIFIER_DEVIOTLB_UNMAP)) {
+        error_setg_errno(errp, ENOTSUP,
+                         "device %02x.%02x.%x requires device IOTLB mode",
+                         pci_bus_num(vtd_as->bus), PCI_SLOT(vtd_as->devfn),
+                         PCI_FUNC(vtd_as->devfn));
+        return -ENOTSUP;
+    }
 
     /* Update per-address-space notifier flags */
     vtd_as->notifier_flags = new;
@@ -3831,7 +3850,7 @@ static void vtd_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n)
                 .domain_id = vtd_get_domain_id(s, &ce, vtd_as->pasid),
             };
 
-            vtd_page_walk(s, &ce, 0, ~0ULL, &info, vtd_as->pasid);
+            vtd_page_walk(s, &ce, n->start, n->end, &info, vtd_as->pasid);
         }
     } else {
         trace_vtd_replay_ce_invalid(bus_n, PCI_SLOT(vtd_as->devfn),
diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c
index 68c2201..3d606a2 100644
--- a/hw/i386/microvm.c
+++ b/hw/i386/microvm.c
@@ -328,7 +328,7 @@ static void microvm_memory_init(MicrovmMachineState *mms)
     rom_set_fw(fw_cfg);
 
     if (machine->kernel_filename != NULL) {
-        x86_load_linux(x86ms, fw_cfg, 0, true, false);
+        x86_load_linux(x86ms, fw_cfg, 0, true);
     }
 
     if (mms->option_roms) {
@@ -376,8 +376,7 @@ static void microvm_fix_kernel_cmdline(MachineState *machine)
     MicrovmMachineState *mms = MICROVM_MACHINE(machine);
     BusState *bus;
     BusChild *kid;
-    char *cmdline, *existing_cmdline;
-    size_t len;
+    char *cmdline;
 
     /*
      * Find MMIO transports with attached devices, and add them to the kernel
@@ -386,8 +385,7 @@ static void microvm_fix_kernel_cmdline(MachineState *machine)
      * Yes, this is a hack, but one that heavily improves the UX without
      * introducing any significant issues.
      */
-    existing_cmdline = fw_cfg_read_bytes_ptr(x86ms->fw_cfg, FW_CFG_CMDLINE_DATA);
-    cmdline = g_strdup(existing_cmdline);
+    cmdline = g_strdup(machine->kernel_cmdline);
     bus = sysbus_get_default();
     QTAILQ_FOREACH(kid, &bus->children, sibling) {
         DeviceState *dev = kid->child;
@@ -411,12 +409,9 @@ static void microvm_fix_kernel_cmdline(MachineState *machine)
         }
     }
 
-    len = strlen(cmdline);
-    if (len > VIRTIO_CMDLINE_TOTAL_MAX_LEN + strlen(existing_cmdline)) {
-        fprintf(stderr, "qemu: virtio mmio cmdline too large, skipping\n");
-    } else {
-        memcpy(existing_cmdline, cmdline, len + 1);
-    }
+    fw_cfg_modify_i32(x86ms->fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(cmdline) + 1);
+    fw_cfg_modify_string(x86ms->fw_cfg, FW_CFG_CMDLINE_DATA, cmdline);
+
     g_free(cmdline);
 }
 
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index fd17ce7..7bebea5 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -810,7 +810,7 @@ void xen_load_linux(PCMachineState *pcms)
     rom_set_fw(fw_cfg);
 
     x86_load_linux(x86ms, fw_cfg, pcmc->acpi_data_size,
-                   pcmc->pvh_enabled, pcmc->legacy_no_rng_seed);
+                   pcmc->pvh_enabled);
     for (i = 0; i < nb_option_roms; i++) {
         assert(!strcmp(option_rom[i].name, "linuxboot.bin") ||
                !strcmp(option_rom[i].name, "linuxboot_dma.bin") ||
@@ -1130,7 +1130,7 @@ void pc_memory_init(PCMachineState *pcms,
 
     if (linux_boot) {
         x86_load_linux(x86ms, fw_cfg, pcmc->acpi_data_size,
-                       pcmc->pvh_enabled, pcmc->legacy_no_rng_seed);
+                       pcmc->pvh_enabled);
     }
 
     for (i = 0; i < nb_option_roms; i++) {
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 126b6c1..2f16011 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -477,9 +477,7 @@ DEFINE_I440FX_MACHINE(v7_2, "pc-i440fx-7.2", NULL,
 
 static void pc_i440fx_7_1_machine_options(MachineClass *m)
 {
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_7_2_machine_options(m);
-    pcmc->legacy_no_rng_seed = true;
     compat_props_add(m->compat_props, hw_compat_7_1, hw_compat_7_1_len);
     compat_props_add(m->compat_props, pc_compat_7_1, pc_compat_7_1_len);
 }
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 09004f3..797ba34 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -395,9 +395,7 @@ DEFINE_Q35_MACHINE(v7_2, "pc-q35-7.2", NULL,
 
 static void pc_q35_7_1_machine_options(MachineClass *m)
 {
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_7_2_machine_options(m);
-    pcmc->legacy_no_rng_seed = true;
     compat_props_add(m->compat_props, hw_compat_7_1, hw_compat_7_1_len);
     compat_props_add(m->compat_props, pc_compat_7_1, pc_compat_7_1_len);
 }
diff --git a/hw/i386/x86.c b/hw/i386/x86.c
index a56b10b..a88a126 100644
--- a/hw/i386/x86.c
+++ b/hw/i386/x86.c
@@ -26,7 +26,6 @@
 #include "qemu/cutils.h"
 #include "qemu/units.h"
 #include "qemu/datadir.h"
-#include "qemu/guest-random.h"
 #include "qapi/error.h"
 #include "qapi/qapi-visit-common.h"
 #include "qapi/clone-visitor.h"
@@ -36,7 +35,6 @@
 #include "sysemu/whpx.h"
 #include "sysemu/numa.h"
 #include "sysemu/replay.h"
-#include "sysemu/reset.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/cpu-timers.h"
 #include "sysemu/xen.h"
@@ -49,7 +47,6 @@
 #include "hw/intc/i8259.h"
 #include "hw/rtc/mc146818rtc.h"
 #include "target/i386/sev.h"
-#include "hw/i386/microvm.h"
 
 #include "hw/acpi/cpu_hotplug.h"
 #include "hw/irq.h"
@@ -675,12 +672,12 @@ DeviceState *ioapic_init_secondary(GSIState *gsi_state)
     return dev;
 }
 
-typedef struct SetupData {
+struct setup_data {
     uint64_t next;
     uint32_t type;
     uint32_t len;
     uint8_t data[];
-} __attribute__((packed)) SetupData;
+} __attribute__((packed));
 
 
 /*
@@ -787,35 +784,10 @@ static bool load_elfboot(const char *kernel_filename,
     return true;
 }
 
-typedef struct SetupDataFixup {
-    void *pos;
-    hwaddr orig_val, new_val;
-    uint32_t addr;
-} SetupDataFixup;
-
-static void fixup_setup_data(void *opaque)
-{
-    SetupDataFixup *fixup = opaque;
-    stq_p(fixup->pos, fixup->new_val);
-}
-
-static void reset_setup_data(void *opaque)
-{
-    SetupDataFixup *fixup = opaque;
-    stq_p(fixup->pos, fixup->orig_val);
-}
-
-static void reset_rng_seed(void *opaque)
-{
-    SetupData *setup_data = opaque;
-    qemu_guest_getrandom_nofail(setup_data->data, le32_to_cpu(setup_data->len));
-}
-
 void x86_load_linux(X86MachineState *x86ms,
                     FWCfgState *fw_cfg,
                     int acpi_data_size,
-                    bool pvh_enabled,
-                    bool legacy_no_rng_seed)
+                    bool pvh_enabled)
 {
     bool linuxboot_dma_enabled = X86_MACHINE_GET_CLASS(x86ms)->fwcfg_dma_enabled;
     uint16_t protocol;
@@ -823,26 +795,19 @@ void x86_load_linux(X86MachineState *x86ms,
     int dtb_size, setup_data_offset;
     uint32_t initrd_max;
     uint8_t header[8192], *setup, *kernel;
-    hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0, first_setup_data = 0;
+    hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0;
     FILE *f;
     char *vmode;
     MachineState *machine = MACHINE(x86ms);
-    SetupData *setup_data;
+    struct setup_data *setup_data;
     const char *kernel_filename = machine->kernel_filename;
     const char *initrd_filename = machine->initrd_filename;
     const char *dtb_filename = machine->dtb;
-    char *kernel_cmdline;
+    const char *kernel_cmdline = machine->kernel_cmdline;
     SevKernelLoaderContext sev_load_ctx = {};
-    enum { RNG_SEED_LENGTH = 32 };
 
-    /*
-     * Add the NUL terminator, some padding for the microvm cmdline fiddling
-     * hack, and then align to 16 bytes as a paranoia measure
-     */
-    cmdline_size = (strlen(machine->kernel_cmdline) + 1 +
-                    VIRTIO_CMDLINE_TOTAL_MAX_LEN + 16) & ~15;
-    /* Make a copy, since we might append arbitrary bytes to it later. */
-    kernel_cmdline = g_strndup(machine->kernel_cmdline, cmdline_size);
+    /* Align to 16 bytes as a paranoia measure */
+    cmdline_size = (strlen(kernel_cmdline) + 16) & ~15;
 
     /* load the kernel header */
     f = fopen(kernel_filename, "rb");
@@ -983,6 +948,12 @@ void x86_load_linux(X86MachineState *x86ms,
         initrd_max = x86ms->below_4g_mem_size - acpi_data_size - 1;
     }
 
+    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr);
+    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(kernel_cmdline) + 1);
+    fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline);
+    sev_load_ctx.cmdline_data = (char *)kernel_cmdline;
+    sev_load_ctx.cmdline_size = strlen(kernel_cmdline) + 1;
+
     if (protocol >= 0x202) {
         stl_p(header + 0x228, cmdline_addr);
     } else {
@@ -1109,45 +1080,20 @@ void x86_load_linux(X86MachineState *x86ms,
             exit(1);
         }
 
-        setup_data_offset = cmdline_size;
-        cmdline_size += sizeof(SetupData) + dtb_size;
-        kernel_cmdline = g_realloc(kernel_cmdline, cmdline_size);
-        setup_data = (void *)kernel_cmdline + setup_data_offset;
-        setup_data->next = cpu_to_le64(first_setup_data);
-        first_setup_data = cmdline_addr + setup_data_offset;
+        setup_data_offset = QEMU_ALIGN_UP(kernel_size, 16);
+        kernel_size = setup_data_offset + sizeof(struct setup_data) + dtb_size;
+        kernel = g_realloc(kernel, kernel_size);
+
+        stq_p(header + 0x250, prot_addr + setup_data_offset);
+
+        setup_data = (struct setup_data *)(kernel + setup_data_offset);
+        setup_data->next = 0;
         setup_data->type = cpu_to_le32(SETUP_DTB);
         setup_data->len = cpu_to_le32(dtb_size);
-        load_image_size(dtb_filename, setup_data->data, dtb_size);
-    }
 
-    if (!legacy_no_rng_seed && protocol >= 0x209) {
-        setup_data_offset = cmdline_size;
-        cmdline_size += sizeof(SetupData) + RNG_SEED_LENGTH;
-        kernel_cmdline = g_realloc(kernel_cmdline, cmdline_size);
-        setup_data = (void *)kernel_cmdline + setup_data_offset;
-        setup_data->next = cpu_to_le64(first_setup_data);
-        first_setup_data = cmdline_addr + setup_data_offset;
-        setup_data->type = cpu_to_le32(SETUP_RNG_SEED);
-        setup_data->len = cpu_to_le32(RNG_SEED_LENGTH);
-        qemu_guest_getrandom_nofail(setup_data->data, RNG_SEED_LENGTH);
-        qemu_register_reset_nosnapshotload(reset_rng_seed, setup_data);
-        fw_cfg_add_bytes_callback(fw_cfg, FW_CFG_KERNEL_DATA, reset_rng_seed, NULL,
-                                  setup_data, kernel, kernel_size, true);
-    } else {
-        fw_cfg_add_bytes(fw_cfg, FW_CFG_KERNEL_DATA, kernel, kernel_size);
+        load_image_size(dtb_filename, setup_data->data, dtb_size);
     }
 
-    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr);
-    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, cmdline_size);
-    fw_cfg_add_bytes(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline, cmdline_size);
-    sev_load_ctx.cmdline_data = (char *)kernel_cmdline;
-    sev_load_ctx.cmdline_size = cmdline_size;
-
-    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, prot_addr);
-    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, kernel_size);
-    sev_load_ctx.kernel_data = (char *)kernel;
-    sev_load_ctx.kernel_size = kernel_size;
-
     /*
      * If we're starting an encrypted VM, it will be OVMF based, which uses the
      * efi stub for booting and doesn't require any values to be placed in the
@@ -1155,21 +1101,17 @@ void x86_load_linux(X86MachineState *x86ms,
      * kernel on the other side of the fw_cfg interface matches the hash of the
      * file the user passed in.
      */
-    if (!sev_enabled() && first_setup_data) {
-        SetupDataFixup *fixup = g_malloc(sizeof(*fixup));
-
+    if (!sev_enabled()) {
         memcpy(setup, header, MIN(sizeof(header), setup_size));
-        /* Offset 0x250 is a pointer to the first setup_data link. */
-        fixup->pos = setup + 0x250;
-        fixup->orig_val = ldq_p(fixup->pos);
-        fixup->new_val = first_setup_data;
-        fixup->addr = cpu_to_le32(real_addr);
-        fw_cfg_add_bytes_callback(fw_cfg, FW_CFG_SETUP_ADDR, fixup_setup_data, NULL,
-                                  fixup, &fixup->addr, sizeof(fixup->addr), true);
-        qemu_register_reset(reset_setup_data, fixup);
-    } else {
-        fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_ADDR, real_addr);
     }
+
+    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, prot_addr);
+    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, kernel_size);
+    fw_cfg_add_bytes(fw_cfg, FW_CFG_KERNEL_DATA, kernel, kernel_size);
+    sev_load_ctx.kernel_data = (char *)kernel;
+    sev_load_ctx.kernel_size = kernel_size;
+
+    fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_ADDR, real_addr);
     fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, setup_size);
     fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, setup, setup_size);
     sev_load_ctx.setup_data = (char *)setup;