hw/i386: pass RNG seed via setup_data entry

Tiny machines optimized for fast boot time generally don't use EFI,
which means a random seed has to be supplied some other way. For this
purpose, Linux (≥5.20) supports passing a seed in the setup_data table
with SETUP_RNG_SEED, specially intended for hypervisors, kexec, and
specialized bootloaders. The linked commit shows the upstream kernel
implementation.

At Paolo's request, we don't pass these to versioned machine types ≤7.0.

Link: https://git.kernel.org/tip/tip/c/68b8e9713c8
Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Eduardo Habkost <eduardo@habkost.net>
Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: Philippe Mathieu-Daudé <f4bug@amsat.org>
Cc: Laurent Vivier <laurent@vivier.eu>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Message-Id: <20220721125636.446842-1-Jason@zx2c4.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

5 files changed, 29 insertions, 7 deletions

diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c
index dc929727dc..7fe8cce03e 100644
--- a/hw/i386/microvm.c
+++ b/hw/i386/microvm.c
@@ -332,7 +332,7 @@ 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);
+        x86_load_linux(x86ms, fw_cfg, 0, true, false);
     }
 
     if (mms->option_roms) {
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 774cb2bf07..d2b5823ffb 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -796,7 +796,7 @@ 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->pvh_enabled, pcmc->legacy_no_rng_seed);
     for (i = 0; i < nb_option_roms; i++) {
         assert(!strcmp(option_rom[i].name, "linuxboot.bin") ||
                !strcmp(option_rom[i].name, "linuxboot_dma.bin") ||
@@ -992,7 +992,7 @@ void pc_memory_init(PCMachineState *pcms,
 
     if (linux_boot) {
         x86_load_linux(x86ms, fw_cfg, pcmc->acpi_data_size,
-                       pcmc->pvh_enabled);
+                       pcmc->pvh_enabled, pcmc->legacy_no_rng_seed);
     }
 
     for (i = 0; i < nb_option_roms; i++) {
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index a234989ac3..fbf9465318 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -438,9 +438,11 @@ DEFINE_I440FX_MACHINE(v7_1, "pc-i440fx-7.1", NULL,
 
 static void pc_i440fx_7_0_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_7_1_machine_options(m);
     m->alias = NULL;
     m->is_default = false;
+    pcmc->legacy_no_rng_seed = true;
     compat_props_add(m->compat_props, hw_compat_7_0, hw_compat_7_0_len);
     compat_props_add(m->compat_props, pc_compat_7_0, pc_compat_7_0_len);
 }
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index f96cbd04e2..12cc76aaf8 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -375,8 +375,10 @@ DEFINE_Q35_MACHINE(v7_1, "pc-q35-7.1", NULL,
 
 static void pc_q35_7_0_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_7_1_machine_options(m);
     m->alias = NULL;
+    pcmc->legacy_no_rng_seed = true;
     compat_props_add(m->compat_props, hw_compat_7_0, hw_compat_7_0_len);
     compat_props_add(m->compat_props, pc_compat_7_0, pc_compat_7_0_len);
 }
diff --git a/hw/i386/x86.c b/hw/i386/x86.c
index 6003b4b2df..ecea25d249 100644
--- a/hw/i386/x86.c
+++ b/hw/i386/x86.c
@@ -26,6 +26,7 @@
 #include "qemu/cutils.h"
 #include "qemu/units.h"
 #include "qemu/datadir.h"
+#include "qemu/guest-random.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qapi-visit-common.h"
@@ -766,7 +767,8 @@ static bool load_elfboot(const char *kernel_filename,
 void x86_load_linux(X86MachineState *x86ms,
                     FWCfgState *fw_cfg,
                     int acpi_data_size,
-                    bool pvh_enabled)
+                    bool pvh_enabled,
+                    bool legacy_no_rng_seed)
 {
     bool linuxboot_dma_enabled = X86_MACHINE_GET_CLASS(x86ms)->fwcfg_dma_enabled;
     uint16_t protocol;
@@ -774,7 +776,7 @@ 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;
+    hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0, first_setup_data = 0;
     FILE *f;
     char *vmode;
     MachineState *machine = MACHINE(x86ms);
@@ -784,6 +786,7 @@ void x86_load_linux(X86MachineState *x86ms,
     const char *dtb_filename = machine->dtb;
     const char *kernel_cmdline = machine->kernel_cmdline;
     SevKernelLoaderContext sev_load_ctx = {};
+    enum { RNG_SEED_LENGTH = 32 };
 
     /* Align to 16 bytes as a paranoia measure */
     cmdline_size = (strlen(kernel_cmdline) + 16) & ~15;
@@ -1063,16 +1066,31 @@ void x86_load_linux(X86MachineState *x86ms,
         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->next = cpu_to_le64(first_setup_data);
+        first_setup_data = prot_addr + setup_data_offset;
         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) {
+        setup_data_offset = QEMU_ALIGN_UP(kernel_size, 16);
+        kernel_size = setup_data_offset + sizeof(struct setup_data) + RNG_SEED_LENGTH;
+        kernel = g_realloc(kernel, kernel_size);
+        setup_data = (struct setup_data *)(kernel + setup_data_offset);
+        setup_data->next = cpu_to_le64(first_setup_data);
+        first_setup_data = prot_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);
+    }
+
+    /* Offset 0x250 is a pointer to the first setup_data link. */
+    stq_p(header + 0x250, first_setup_data);
+
     /*
      * 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