aboutsummaryrefslogtreecommitdiff
path: root/hw
diff options
context:
space:
mode:
authorRichard Henderson <richard.henderson@linaro.org>2024-06-05 07:45:23 -0700
committerRichard Henderson <richard.henderson@linaro.org>2024-06-05 07:45:23 -0700
commitf1572ab94738bd5787b7badcd4bd93a3657f0680 (patch)
tree96304b05bbda566ec6cf33bcbd3be3b84203b45a /hw
parentd16cab541ab9217977e2a39abf3d79f914146741 (diff)
parentfc7a69e177e4ba26d11fcf47b853f85115b35a11 (diff)
Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging
* virtio-blk: remove SCSI passthrough functionality * require x86-64-v2 baseline ISA * SEV-SNP host support * fix xsave.flat with TCG * fixes for CPUID checks done by TCG # -----BEGIN PGP SIGNATURE----- # # iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmZgKVYUHHBib256aW5p # QHJlZGhhdC5jb20ACgkQv/vSX3jHroPKYgf/QkWrNXdjjD3yAsv5LbJFVTVyCYW3 # b4Iax29kEDy8k9wbzfLxOfIk9jXIjmbOMO5ZN9LFiHK6VJxbXslsMh6hm50M3xKe # 49X1Rvf9YuVA7KZX+dWkEuqLYI6Tlgj3HaCilYWfXrjyo6hY3CxzkPV/ChmaeYlV # Ad4Y8biifoUuuEK8OTeTlcDWLhOHlFXylG3AXqULsUsXp0XhWJ9juXQ60eATv/W4 # eCEH7CSmRhYFu2/rV+IrWFYMnskLRTk1OC1/m6yXGPKOzgnOcthuvQfiUgPkbR/d # llY6Ni5Aaf7+XX3S7Avcyvoq8jXzaaMzOrzL98rxYGDR1sYBYO+4h4ZToA== # =qQeP # -----END PGP SIGNATURE----- # gpg: Signature made Wed 05 Jun 2024 02:01:10 AM PDT # gpg: using RSA key F13338574B662389866C7682BFFBD25F78C7AE83 # gpg: issuer "pbonzini@redhat.com" # gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full] # gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" [full] * tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (46 commits) hw/i386: Add support for loading BIOS using guest_memfd hw/i386/sev: Use guest_memfd for legacy ROMs memory: Introduce memory_region_init_ram_guest_memfd() i386/sev: Allow measured direct kernel boot on SNP i386/sev: Reorder struct declarations i386/sev: Extract build_kernel_loader_hashes i386/sev: Enable KVM_HC_MAP_GPA_RANGE hcall for SNP guests i386/kvm: Add KVM_EXIT_HYPERCALL handling for KVM_HC_MAP_GPA_RANGE i386/sev: Invoke launch_updata_data() for SNP class i386/sev: Invoke launch_updata_data() for SEV class hw/i386/sev: Add support to encrypt BIOS when SEV-SNP is enabled i386/sev: Add support for SNP CPUID validation i386/sev: Add support for populating OVMF metadata pages hw/i386/sev: Add function to get SEV metadata from OVMF header i386/sev: Set CPU state to protected once SNP guest payload is finalized i386/sev: Add handling to encrypt/finalize guest launch data i386/sev: Add the SNP launch start context i386/sev: Update query-sev QAPI format to handle SEV-SNP i386/sev: Add a class method to determine KVM VM type for SNP guests i386/sev: Don't return launch measurements for SEV-SNP guests ... Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'hw')
-rw-r--r--hw/block/virtio-blk.c166
-rw-r--r--hw/core/machine.c4
-rw-r--r--hw/i386/pc.c14
-rw-r--r--hw/i386/pc_sysfw.c35
-rw-r--r--hw/i386/x86-common.c19
-rw-r--r--hw/misc/pvpanic-isa.c2
-rw-r--r--hw/misc/pvpanic-pci.c2
-rw-r--r--hw/misc/pvpanic.c2
8 files changed, 62 insertions, 182 deletions
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index bb86e65f65..73bdfd6122 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -172,57 +172,6 @@ static void virtio_blk_discard_write_zeroes_complete(void *opaque, int ret)
virtio_blk_free_request(req);
}
-#ifdef __linux__
-
-typedef struct {
- VirtIOBlockReq *req;
- struct sg_io_hdr hdr;
-} VirtIOBlockIoctlReq;
-
-static void virtio_blk_ioctl_complete(void *opaque, int status)
-{
- VirtIOBlockIoctlReq *ioctl_req = opaque;
- VirtIOBlockReq *req = ioctl_req->req;
- VirtIOBlock *s = req->dev;
- VirtIODevice *vdev = VIRTIO_DEVICE(s);
- struct virtio_scsi_inhdr *scsi;
- struct sg_io_hdr *hdr;
-
- scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
-
- if (status) {
- status = VIRTIO_BLK_S_UNSUPP;
- virtio_stl_p(vdev, &scsi->errors, 255);
- goto out;
- }
-
- hdr = &ioctl_req->hdr;
- /*
- * From SCSI-Generic-HOWTO: "Some lower level drivers (e.g. ide-scsi)
- * clear the masked_status field [hence status gets cleared too, see
- * block/scsi_ioctl.c] even when a CHECK_CONDITION or COMMAND_TERMINATED
- * status has occurred. However they do set DRIVER_SENSE in driver_status
- * field. Also a (sb_len_wr > 0) indicates there is a sense buffer.
- */
- if (hdr->status == 0 && hdr->sb_len_wr > 0) {
- hdr->status = CHECK_CONDITION;
- }
-
- virtio_stl_p(vdev, &scsi->errors,
- hdr->status | (hdr->msg_status << 8) |
- (hdr->host_status << 16) | (hdr->driver_status << 24));
- virtio_stl_p(vdev, &scsi->residual, hdr->resid);
- virtio_stl_p(vdev, &scsi->sense_len, hdr->sb_len_wr);
- virtio_stl_p(vdev, &scsi->data_len, hdr->dxfer_len);
-
-out:
- virtio_blk_req_complete(req, status);
- virtio_blk_free_request(req);
- g_free(ioctl_req);
-}
-
-#endif
-
static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s, VirtQueue *vq)
{
VirtIOBlockReq *req = virtqueue_pop(vq, sizeof(VirtIOBlockReq));
@@ -233,20 +182,14 @@ static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s, VirtQueue *vq)
return req;
}
-static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req)
+static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
{
- int status = VIRTIO_BLK_S_OK;
- struct virtio_scsi_inhdr *scsi = NULL;
+ int status;
+ struct virtio_scsi_inhdr *scsi;
VirtIOBlock *blk = req->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(blk);
VirtQueueElement *elem = &req->elem;
-#ifdef __linux__
- int i;
- VirtIOBlockIoctlReq *ioctl_req;
- BlockAIOCB *acb;
-#endif
-
/*
* We require at least one output segment each for the virtio_blk_outhdr
* and the SCSI command block.
@@ -262,95 +205,16 @@ static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req)
/*
* The scsi inhdr is placed in the second-to-last input segment, just
* before the regular inhdr.
+ *
+ * Just put anything nonzero so that the ioctl fails in the guest.
*/
scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base;
-
- if (!virtio_has_feature(blk->host_features, VIRTIO_BLK_F_SCSI)) {
- status = VIRTIO_BLK_S_UNSUPP;
- goto fail;
- }
-
- /*
- * No support for bidirection commands yet.
- */
- if (elem->out_num > 2 && elem->in_num > 3) {
- status = VIRTIO_BLK_S_UNSUPP;
- goto fail;
- }
-
-#ifdef __linux__
- ioctl_req = g_new0(VirtIOBlockIoctlReq, 1);
- ioctl_req->req = req;
- ioctl_req->hdr.interface_id = 'S';
- ioctl_req->hdr.cmd_len = elem->out_sg[1].iov_len;
- ioctl_req->hdr.cmdp = elem->out_sg[1].iov_base;
- ioctl_req->hdr.dxfer_len = 0;
-
- if (elem->out_num > 2) {
- /*
- * If there are more than the minimally required 2 output segments
- * there is write payload starting from the third iovec.
- */
- ioctl_req->hdr.dxfer_direction = SG_DXFER_TO_DEV;
- ioctl_req->hdr.iovec_count = elem->out_num - 2;
-
- for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
- ioctl_req->hdr.dxfer_len += elem->out_sg[i + 2].iov_len;
- }
-
- ioctl_req->hdr.dxferp = elem->out_sg + 2;
-
- } else if (elem->in_num > 3) {
- /*
- * If we have more than 3 input segments the guest wants to actually
- * read data.
- */
- ioctl_req->hdr.dxfer_direction = SG_DXFER_FROM_DEV;
- ioctl_req->hdr.iovec_count = elem->in_num - 3;
- for (i = 0; i < ioctl_req->hdr.iovec_count; i++) {
- ioctl_req->hdr.dxfer_len += elem->in_sg[i].iov_len;
- }
-
- ioctl_req->hdr.dxferp = elem->in_sg;
- } else {
- /*
- * Some SCSI commands don't actually transfer any data.
- */
- ioctl_req->hdr.dxfer_direction = SG_DXFER_NONE;
- }
-
- ioctl_req->hdr.sbp = elem->in_sg[elem->in_num - 3].iov_base;
- ioctl_req->hdr.mx_sb_len = elem->in_sg[elem->in_num - 3].iov_len;
-
- acb = blk_aio_ioctl(blk->blk, SG_IO, &ioctl_req->hdr,
- virtio_blk_ioctl_complete, ioctl_req);
- if (!acb) {
- g_free(ioctl_req);
- status = VIRTIO_BLK_S_UNSUPP;
- goto fail;
- }
- return -EINPROGRESS;
-#else
- abort();
-#endif
+ virtio_stl_p(vdev, &scsi->errors, 255);
+ status = VIRTIO_BLK_S_UNSUPP;
fail:
- /* Just put anything nonzero so that the ioctl fails in the guest. */
- if (scsi) {
- virtio_stl_p(vdev, &scsi->errors, 255);
- }
- return status;
-}
-
-static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
-{
- int status;
-
- status = virtio_blk_handle_scsi_req(req);
- if (status != -EINPROGRESS) {
- virtio_blk_req_complete(req, status);
- virtio_blk_free_request(req);
- }
+ virtio_blk_req_complete(req, status);
+ virtio_blk_free_request(req);
}
static inline void submit_requests(VirtIOBlock *s, MultiReqBuffer *mrb,
@@ -1379,13 +1243,9 @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
- if (virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
- if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_SCSI)) {
- error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0");
- return 0;
- }
- } else {
+ if (!virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
virtio_clear_feature(&features, VIRTIO_F_ANY_LAYOUT);
+ /* Added for historical reasons, removing it could break migration. */
virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
}
@@ -2132,10 +1992,6 @@ static Property virtio_blk_properties[] = {
DEFINE_PROP_STRING("serial", VirtIOBlock, conf.serial),
DEFINE_PROP_BIT64("config-wce", VirtIOBlock, host_features,
VIRTIO_BLK_F_CONFIG_WCE, true),
-#ifdef __linux__
- DEFINE_PROP_BIT64("scsi", VirtIOBlock, host_features,
- VIRTIO_BLK_F_SCSI, false),
-#endif
DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0,
true),
DEFINE_PROP_UINT16("num-queues", VirtIOBlock, conf.num_queues,
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 8087026b45..77a356f232 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -265,8 +265,6 @@ GlobalProperty hw_compat_2_5[] = {
const size_t hw_compat_2_5_len = G_N_ELEMENTS(hw_compat_2_5);
GlobalProperty hw_compat_2_4[] = {
- /* Optional because the 'scsi' property is Linux-only */
- { "virtio-blk-device", "scsi", "true", .optional = true },
{ "e1000", "extra_mac_registers", "off" },
{ "virtio-pci", "x-disable-pcie", "on" },
{ "virtio-pci", "migrate-extra", "off" },
@@ -1218,7 +1216,7 @@ bool machine_mem_merge(MachineState *machine)
bool machine_require_guest_memfd(MachineState *machine)
{
- return machine->require_guest_memfd;
+ return machine->cgs && machine->cgs->require_guest_memfd;
}
static char *cpu_slot_to_string(const CPUArchId *cpu)
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 7b638da7aa..0469af00a7 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -62,6 +62,7 @@
#include "hw/mem/memory-device.h"
#include "e820_memory_layout.h"
#include "trace.h"
+#include "sev.h"
#include CONFIG_DEVICES
#ifdef CONFIG_XEN_EMU
@@ -1022,10 +1023,15 @@ void pc_memory_init(PCMachineState *pcms,
pc_system_firmware_init(pcms, rom_memory);
option_rom_mr = g_malloc(sizeof(*option_rom_mr));
- memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE,
- &error_fatal);
- if (pcmc->pci_enabled) {
- memory_region_set_readonly(option_rom_mr, true);
+ if (machine_require_guest_memfd(machine)) {
+ memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom",
+ PC_ROM_SIZE, &error_fatal);
+ } else {
+ memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE,
+ &error_fatal);
+ if (pcmc->pci_enabled) {
+ memory_region_set_readonly(option_rom_mr, true);
+ }
}
memory_region_add_subregion_overlap(rom_memory,
PC_ROM_MIN_VGA,
diff --git a/hw/i386/pc_sysfw.c b/hw/i386/pc_sysfw.c
index ac88ad4eb9..ef80281d28 100644
--- a/hw/i386/pc_sysfw.c
+++ b/hw/i386/pc_sysfw.c
@@ -40,8 +40,8 @@
#define FLASH_SECTOR_SIZE 4096
-static void pc_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *rom_memory,
- MemoryRegion *flash_mem)
+static void pc_isa_bios_init(PCMachineState *pcms, MemoryRegion *isa_bios,
+ MemoryRegion *rom_memory, MemoryRegion *flash_mem)
{
int isa_bios_size;
uint64_t flash_size;
@@ -51,8 +51,13 @@ static void pc_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *rom_memory,
/* map the last 128KB of the BIOS in ISA space */
isa_bios_size = MIN(flash_size, 128 * KiB);
- memory_region_init_ram(isa_bios, NULL, "isa-bios", isa_bios_size,
- &error_fatal);
+ if (machine_require_guest_memfd(MACHINE(pcms))) {
+ memory_region_init_ram_guest_memfd(isa_bios, NULL, "isa-bios",
+ isa_bios_size, &error_fatal);
+ } else {
+ memory_region_init_ram(isa_bios, NULL, "isa-bios", isa_bios_size,
+ &error_fatal);
+ }
memory_region_add_subregion_overlap(rom_memory,
0x100000 - isa_bios_size,
isa_bios,
@@ -65,7 +70,9 @@ static void pc_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *rom_memory,
((uint8_t*)flash_ptr) + (flash_size - isa_bios_size),
isa_bios_size);
- memory_region_set_readonly(isa_bios, true);
+ if (!machine_require_guest_memfd(current_machine)) {
+ memory_region_set_readonly(isa_bios, true);
+ }
}
static PFlashCFI01 *pc_pflash_create(PCMachineState *pcms,
@@ -148,6 +155,8 @@ static void pc_system_flash_map(PCMachineState *pcms,
assert(PC_MACHINE_GET_CLASS(pcms)->pci_enabled);
for (i = 0; i < ARRAY_SIZE(pcms->flash); i++) {
+ hwaddr gpa;
+
system_flash = pcms->flash[i];
blk = pflash_cfi01_get_blk(system_flash);
if (!blk) {
@@ -177,11 +186,11 @@ static void pc_system_flash_map(PCMachineState *pcms,
}
total_size += size;
+ gpa = 0x100000000ULL - total_size; /* where the flash is mapped */
qdev_prop_set_uint32(DEVICE(system_flash), "num-blocks",
size / FLASH_SECTOR_SIZE);
sysbus_realize_and_unref(SYS_BUS_DEVICE(system_flash), &error_fatal);
- sysbus_mmio_map(SYS_BUS_DEVICE(system_flash), 0,
- 0x100000000ULL - total_size);
+ sysbus_mmio_map(SYS_BUS_DEVICE(system_flash), 0, gpa);
if (i == 0) {
flash_mem = pflash_cfi01_get_memory(system_flash);
@@ -189,14 +198,14 @@ static void pc_system_flash_map(PCMachineState *pcms,
x86_isa_bios_init(&x86ms->isa_bios, rom_memory, flash_mem,
true);
} else {
- pc_isa_bios_init(&x86ms->isa_bios, rom_memory, flash_mem);
+ pc_isa_bios_init(pcms, &x86ms->isa_bios, rom_memory, flash_mem);
}
/* Encrypt the pflash boot ROM */
if (sev_enabled()) {
flash_ptr = memory_region_get_ram_ptr(flash_mem);
flash_size = memory_region_size(flash_mem);
- x86_firmware_configure(flash_ptr, flash_size);
+ x86_firmware_configure(gpa, flash_ptr, flash_size);
}
}
}
@@ -249,7 +258,7 @@ void pc_system_firmware_init(PCMachineState *pcms,
pc_system_flash_cleanup_unused(pcms);
}
-void x86_firmware_configure(void *ptr, int size)
+void x86_firmware_configure(hwaddr gpa, void *ptr, int size)
{
int ret;
@@ -260,12 +269,16 @@ void x86_firmware_configure(void *ptr, int size)
pc_system_parse_ovmf_flash(ptr, size);
if (sev_enabled()) {
+
+ /* Copy the SEV metadata table (if it exists) */
+ pc_system_parse_sev_metadata(ptr, size);
+
ret = sev_es_save_reset_vector(ptr, size);
if (ret) {
error_report("failed to locate and/or save reset vector");
exit(1);
}
- sev_encrypt_flash(ptr, size, &error_fatal);
+ sev_encrypt_flash(gpa, ptr, size, &error_fatal);
}
}
diff --git a/hw/i386/x86-common.c b/hw/i386/x86-common.c
index ee9046d9a8..c0c66a0eb5 100644
--- a/hw/i386/x86-common.c
+++ b/hw/i386/x86-common.c
@@ -1001,8 +1001,13 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware,
(bios_size % 65536) != 0) {
goto bios_error;
}
- memory_region_init_ram(&x86ms->bios, NULL, "pc.bios", bios_size,
- &error_fatal);
+ if (machine_require_guest_memfd(MACHINE(x86ms))) {
+ memory_region_init_ram_guest_memfd(&x86ms->bios, NULL, "pc.bios",
+ bios_size, &error_fatal);
+ } else {
+ memory_region_init_ram(&x86ms->bios, NULL, "pc.bios",
+ bios_size, &error_fatal);
+ }
if (sev_enabled()) {
/*
* The concept of a "reset" simply doesn't exist for
@@ -1013,7 +1018,7 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware,
*/
void *ptr = memory_region_get_ram_ptr(&x86ms->bios);
load_image_size(filename, ptr, bios_size);
- x86_firmware_configure(ptr, bios_size);
+ x86_firmware_configure(0x100000000ULL - bios_size, ptr, bios_size);
} else {
memory_region_set_readonly(&x86ms->bios, !isapc_ram_fw);
ret = rom_add_file_fixed(bios_name, (uint32_t)(-bios_size), -1);
@@ -1023,9 +1028,11 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware,
}
g_free(filename);
- /* map the last 128KB of the BIOS in ISA space */
- x86_isa_bios_init(&x86ms->isa_bios, rom_memory, &x86ms->bios,
- !isapc_ram_fw);
+ if (!machine_require_guest_memfd(MACHINE(x86ms))) {
+ /* map the last 128KB of the BIOS in ISA space */
+ x86_isa_bios_init(&x86ms->isa_bios, rom_memory, &x86ms->bios,
+ !isapc_ram_fw);
+ }
/* map all the bios at the top of memory */
memory_region_add_subregion(rom_memory,
diff --git a/hw/misc/pvpanic-isa.c b/hw/misc/pvpanic-isa.c
index ccec50f61b..b4f84c4110 100644
--- a/hw/misc/pvpanic-isa.c
+++ b/hw/misc/pvpanic-isa.c
@@ -21,7 +21,7 @@
#include "hw/misc/pvpanic.h"
#include "qom/object.h"
#include "hw/isa/isa.h"
-#include "standard-headers/linux/pvpanic.h"
+#include "standard-headers/misc/pvpanic.h"
#include "hw/acpi/acpi_aml_interface.h"
OBJECT_DECLARE_SIMPLE_TYPE(PVPanicISAState, PVPANIC_ISA_DEVICE)
diff --git a/hw/misc/pvpanic-pci.c b/hw/misc/pvpanic-pci.c
index 83be95d0d2..4d44a881da 100644
--- a/hw/misc/pvpanic-pci.c
+++ b/hw/misc/pvpanic-pci.c
@@ -21,7 +21,7 @@
#include "hw/misc/pvpanic.h"
#include "qom/object.h"
#include "hw/pci/pci_device.h"
-#include "standard-headers/linux/pvpanic.h"
+#include "standard-headers/misc/pvpanic.h"
OBJECT_DECLARE_SIMPLE_TYPE(PVPanicPCIState, PVPANIC_PCI_DEVICE)
diff --git a/hw/misc/pvpanic.c b/hw/misc/pvpanic.c
index 1540e9091a..80289ecf5f 100644
--- a/hw/misc/pvpanic.c
+++ b/hw/misc/pvpanic.c
@@ -21,7 +21,7 @@
#include "hw/qdev-properties.h"
#include "hw/misc/pvpanic.h"
#include "qom/object.h"
-#include "standard-headers/linux/pvpanic.h"
+#include "standard-headers/misc/pvpanic.h"
static void handle_event(int event)
{
generated by cgit v1.2.3 (git 2.26.2) at 2025-03-17 07:36:20 +0000