diff options
158 files changed, 5994 insertions, 3616 deletions
diff --git a/.gitlab-ci.d/cirrus/freebsd-13.vars b/.gitlab-ci.d/cirrus/freebsd-13.vars index 3785afca36..29ab9645f9 100644 --- a/.gitlab-ci.d/cirrus/freebsd-13.vars +++ b/.gitlab-ci.d/cirrus/freebsd-13.vars @@ -11,6 +11,6 @@ MAKE='/usr/local/bin/gmake' NINJA='/usr/local/bin/ninja' PACKAGING_COMMAND='pkg' PIP3='/usr/local/bin/pip-3.8' -PKGS='alsa-lib bash bison bzip2 ca_root_nss capstone4 ccache cmocka ctags curl cyrus-sasl dbus diffutils dtc flex fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 json-c libepoxy libffi libgcrypt libjpeg-turbo libnfs libslirp libspice-server libssh libtasn1 llvm lzo2 meson mtools ncurses nettle ninja opencv pixman pkgconf png py39-numpy py39-pillow py39-pip py39-sphinx py39-sphinx_rtd_theme py39-tomli py39-yaml python3 rpm2cpio sdl2 sdl2_image snappy sndio socat spice-protocol tesseract usbredir virglrenderer vte3 xorriso zstd' +PKGS='alsa-lib bash bison bzip2 ca_root_nss capstone4 ccache cmocka ctags curl cyrus-sasl dbus diffutils dtc flex fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 json-c libepoxy libffi libgcrypt libjpeg-turbo libnfs libslirp libspice-server libssh libtasn1 llvm lzo2 meson mtools ncurses nettle ninja opencv pixman pkgconf png py311-numpy py311-pillow py311-pip py311-sphinx py311-sphinx_rtd_theme py311-tomli py311-yaml python3 rpm2cpio sdl2 sdl2_image snappy sndio socat spice-protocol tesseract usbredir virglrenderer vte3 xorriso zstd' PYPI_PKGS='' PYTHON='/usr/local/bin/python3' diff --git a/MAINTAINERS b/MAINTAINERS index f8df6940fa..0645cbf59a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1728,7 +1728,6 @@ S: Maintained F: hw/sparc/leon3.c F: hw/*/grlib* F: include/hw/*/grlib* -F: tests/avocado/machine_sparc_leon3.py S390 Machines ------------- @@ -2011,6 +2010,7 @@ F: hw/pci-bridge/* F: qapi/pci.json F: docs/pci* F: docs/specs/*pci* +F: docs/system/sriov.rst PCIE DOE M: Huai-Cheng Kuo <hchkuo@avery-design.com.tw> @@ -2210,6 +2210,7 @@ F: docs/devel/vfio-iommufd.rst vhost M: Michael S. Tsirkin <mst@redhat.com> +R: Stefano Garzarella <sgarzare@redhat.com> S: Supported F: hw/*/*vhost* F: docs/interop/vhost-user.json @@ -3400,6 +3401,12 @@ F: tests/qtest/*tpm* F: docs/specs/tpm.rst T: git https://github.com/stefanberger/qemu-tpm.git tpm-next +SPDM +M: Alistair Francis <alistair.francis@wdc.com> +S: Maintained +F: backends/spdm-socket.c +F: include/sysemu/spdm-socket.h + Checkpatch S: Odd Fixes F: scripts/checkpatch.pl @@ -3659,6 +3666,7 @@ F: tests/uefi-test-tools/ VT-d Emulation M: Michael S. Tsirkin <mst@redhat.com> R: Jason Wang <jasowang@redhat.com> +R: Yi Liu <yi.l.liu@intel.com> S: Supported F: hw/i386/intel_iommu.c F: hw/i386/intel_iommu_internal.h diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 480c7119d1..67b773692f 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -340,14 +340,71 @@ err: return ret; } +void kvm_park_vcpu(CPUState *cpu) +{ + struct KVMParkedVcpu *vcpu; + + trace_kvm_park_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu)); + + vcpu = g_malloc0(sizeof(*vcpu)); + vcpu->vcpu_id = kvm_arch_vcpu_id(cpu); + vcpu->kvm_fd = cpu->kvm_fd; + QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node); +} + +int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id) +{ + struct KVMParkedVcpu *cpu; + int kvm_fd = -ENOENT; + + QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) { + if (cpu->vcpu_id == vcpu_id) { + QLIST_REMOVE(cpu, node); + kvm_fd = cpu->kvm_fd; + g_free(cpu); + } + } + + trace_kvm_unpark_vcpu(vcpu_id, kvm_fd > 0 ? "unparked" : "!found parked"); + + return kvm_fd; +} + +int kvm_create_vcpu(CPUState *cpu) +{ + unsigned long vcpu_id = kvm_arch_vcpu_id(cpu); + KVMState *s = kvm_state; + int kvm_fd; + + /* check if the KVM vCPU already exist but is parked */ + kvm_fd = kvm_unpark_vcpu(s, vcpu_id); + if (kvm_fd < 0) { + /* vCPU not parked: create a new KVM vCPU */ + kvm_fd = kvm_vm_ioctl(s, KVM_CREATE_VCPU, vcpu_id); + if (kvm_fd < 0) { + error_report("KVM_CREATE_VCPU IOCTL failed for vCPU %lu", vcpu_id); + return kvm_fd; + } + } + + cpu->kvm_fd = kvm_fd; + cpu->kvm_state = s; + cpu->vcpu_dirty = true; + cpu->dirty_pages = 0; + cpu->throttle_us_per_full = 0; + + trace_kvm_create_vcpu(cpu->cpu_index, vcpu_id, kvm_fd); + + return 0; +} + static int do_kvm_destroy_vcpu(CPUState *cpu) { KVMState *s = kvm_state; long mmap_size; - struct KVMParkedVcpu *vcpu = NULL; int ret = 0; - trace_kvm_destroy_vcpu(); + trace_kvm_destroy_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu)); ret = kvm_arch_destroy_vcpu(cpu); if (ret < 0) { @@ -373,10 +430,7 @@ static int do_kvm_destroy_vcpu(CPUState *cpu) } } - vcpu = g_malloc0(sizeof(*vcpu)); - vcpu->vcpu_id = kvm_arch_vcpu_id(cpu); - vcpu->kvm_fd = cpu->kvm_fd; - QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node); + kvm_park_vcpu(cpu); err: return ret; } @@ -389,24 +443,6 @@ void kvm_destroy_vcpu(CPUState *cpu) } } -static int kvm_get_vcpu(KVMState *s, unsigned long vcpu_id) -{ - struct KVMParkedVcpu *cpu; - - QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) { - if (cpu->vcpu_id == vcpu_id) { - int kvm_fd; - - QLIST_REMOVE(cpu, node); - kvm_fd = cpu->kvm_fd; - g_free(cpu); - return kvm_fd; - } - } - - return kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)vcpu_id); -} - int kvm_init_vcpu(CPUState *cpu, Error **errp) { KVMState *s = kvm_state; @@ -415,19 +451,14 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp) trace_kvm_init_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu)); - ret = kvm_get_vcpu(s, kvm_arch_vcpu_id(cpu)); + ret = kvm_create_vcpu(cpu); if (ret < 0) { - error_setg_errno(errp, -ret, "kvm_init_vcpu: kvm_get_vcpu failed (%lu)", + error_setg_errno(errp, -ret, + "kvm_init_vcpu: kvm_create_vcpu failed (%lu)", kvm_arch_vcpu_id(cpu)); goto err; } - cpu->kvm_fd = ret; - cpu->kvm_state = s; - cpu->vcpu_dirty = true; - cpu->dirty_pages = 0; - cpu->throttle_us_per_full = 0; - mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0); if (mmap_size < 0) { ret = mmap_size; diff --git a/accel/kvm/kvm-cpus.h b/accel/kvm/kvm-cpus.h index ca40add32c..171b22fd29 100644 --- a/accel/kvm/kvm-cpus.h +++ b/accel/kvm/kvm-cpus.h @@ -22,5 +22,4 @@ bool kvm_supports_guest_debug(void); int kvm_insert_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len); int kvm_remove_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len); void kvm_remove_all_breakpoints(CPUState *cpu); - #endif /* KVM_CPUS_H */ diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events index 681ccb667d..37626c1ac5 100644 --- a/accel/kvm/trace-events +++ b/accel/kvm/trace-events @@ -9,6 +9,10 @@ kvm_device_ioctl(int fd, int type, void *arg) "dev fd %d, type 0x%x, arg %p" kvm_failed_reg_get(uint64_t id, const char *msg) "Warning: Unable to retrieve ONEREG %" PRIu64 " from KVM: %s" kvm_failed_reg_set(uint64_t id, const char *msg) "Warning: Unable to set ONEREG %" PRIu64 " to KVM: %s" kvm_init_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu" +kvm_create_vcpu(int cpu_index, unsigned long arch_cpu_id, int kvm_fd) "index: %d, id: %lu, kvm fd: %d" +kvm_destroy_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu" +kvm_park_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu" +kvm_unpark_vcpu(unsigned long arch_cpu_id, const char *msg) "id: %lu %s" kvm_irqchip_commit_routes(void) "" kvm_irqchip_add_msi_route(char *name, int vector, int virq) "dev %s vector %d virq %d" kvm_irqchip_update_msi_route(int virq) "Updating MSI route virq=%d" @@ -25,7 +29,6 @@ kvm_dirty_ring_reaper(const char *s) "%s" kvm_dirty_ring_reap(uint64_t count, int64_t t) "reaped %"PRIu64" pages (took %"PRIi64" us)" kvm_dirty_ring_reaper_kick(const char *reason) "%s" kvm_dirty_ring_flush(int finished) "%d" -kvm_destroy_vcpu(void) "" kvm_failed_get_vcpu_mmap_size(void) "" kvm_cpu_exec(void) "" kvm_interrupt_exit_request(void) "" diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index 9010dad073..8163295f34 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -41,9 +41,6 @@ #include "tb-context.h" #include "internal-common.h" #include "internal-target.h" -#if defined(CONFIG_USER_ONLY) -#include "user-retaddr.h" -#endif /* -icount align implementation. */ diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index b6bae32b99..ec89a085b4 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -85,8 +85,7 @@ static void gen_enable_mem_helper(struct qemu_plugin_tb *ptb, len = insn->mem_cbs->len; arr = g_array_sized_new(false, false, sizeof(struct qemu_plugin_dyn_cb), len); - memcpy(arr->data, insn->mem_cbs->data, - len * sizeof(struct qemu_plugin_dyn_cb)); + g_array_append_vals(arr, insn->mem_cbs->data, len); qemu_plugin_add_dyn_cb_arr(arr); tcg_gen_st_ptr(tcg_constant_ptr((intptr_t)arr), tcg_env, diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index 80d24540ed..7ddc47b0ba 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -33,7 +33,6 @@ #include "tcg/tcg-ldst.h" #include "internal-common.h" #include "internal-target.h" -#include "user-retaddr.h" __thread uintptr_t helper_retaddr; diff --git a/accel/tcg/user-retaddr.h b/accel/tcg/user-retaddr.h deleted file mode 100644 index e0f57e1994..0000000000 --- a/accel/tcg/user-retaddr.h +++ /dev/null @@ -1,28 +0,0 @@ -#ifndef ACCEL_TCG_USER_RETADDR_H -#define ACCEL_TCG_USER_RETADDR_H - -#include "qemu/atomic.h" - -extern __thread uintptr_t helper_retaddr; - -static inline void set_helper_retaddr(uintptr_t ra) -{ - helper_retaddr = ra; - /* - * Ensure that this write is visible to the SIGSEGV handler that - * may be invoked due to a subsequent invalid memory operation. - */ - signal_barrier(); -} - -static inline void clear_helper_retaddr(void) -{ - /* - * Ensure that previous memory operations have succeeded before - * removing the data visible to the signal handler. - */ - signal_barrier(); - helper_retaddr = 0; -} - -#endif diff --git a/audio/dbusaudio.c b/audio/dbusaudio.c index 60fcf643ec..095e739382 100644 --- a/audio/dbusaudio.c +++ b/audio/dbusaudio.c @@ -105,7 +105,7 @@ static size_t dbus_put_buffer_out(HWVoiceOut *hw, void *buf, size_t size) assert(buf == vo->buf + vo->buf_pos && vo->buf_pos + size <= vo->buf_size); vo->buf_pos += size; - trace_dbus_audio_put_buffer_out(size); + trace_dbus_audio_put_buffer_out(vo->buf_pos, vo->buf_size); if (vo->buf_pos < vo->buf_size) { return size; diff --git a/audio/trace-events b/audio/trace-events index ab04f020ce..7e3f1593c8 100644 --- a/audio/trace-events +++ b/audio/trace-events @@ -15,7 +15,7 @@ oss_version(int version) "OSS version = 0x%x" # dbusaudio.c dbus_audio_register(const char *s, const char *dir) "sender = %s, dir = %s" -dbus_audio_put_buffer_out(size_t len) "len = %zu" +dbus_audio_put_buffer_out(size_t pos, size_t size) "buf_pos = %zu, buf_size = %zu" dbus_audio_read(size_t len) "len = %zu" # pwaudio.c diff --git a/backends/Kconfig b/backends/Kconfig index 2cb23f62fa..d3dbe19868 100644 --- a/backends/Kconfig +++ b/backends/Kconfig @@ -3,3 +3,7 @@ source tpm/Kconfig config IOMMUFD bool depends on VFIO + +config SPDM_SOCKET + bool + default y diff --git a/backends/meson.build b/backends/meson.build index 749b491f12..da714b93d1 100644 --- a/backends/meson.build +++ b/backends/meson.build @@ -33,4 +33,6 @@ endif system_ss.add(when: gio, if_true: files('dbus-vmstate.c')) system_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c')) +system_ss.add(when: 'CONFIG_SPDM_SOCKET', if_true: files('spdm-socket.c')) + subdir('tpm') diff --git a/backends/spdm-socket.c b/backends/spdm-socket.c new file mode 100644 index 0000000000..d0663d696c --- /dev/null +++ b/backends/spdm-socket.c @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * QEMU SPDM socket support + * + * This is based on: + * https://github.com/DMTF/spdm-emu/blob/07c0a838bcc1c6207c656ac75885c0603e344b6f/spdm_emu/spdm_emu_common/command.c + * but has been re-written to match QEMU style + * + * Copyright (c) 2021, DMTF. All rights reserved. + * Copyright (c) 2023. Western Digital Corporation or its affiliates. + */ + +#include "qemu/osdep.h" +#include "sysemu/spdm-socket.h" +#include "qapi/error.h" + +static bool read_bytes(const int socket, uint8_t *buffer, + size_t number_of_bytes) +{ + ssize_t number_received = 0; + ssize_t result; + + while (number_received < number_of_bytes) { + result = recv(socket, buffer + number_received, + number_of_bytes - number_received, 0); + if (result <= 0) { + return false; + } + number_received += result; + } + return true; +} + +static bool read_data32(const int socket, uint32_t *data) +{ + bool result; + + result = read_bytes(socket, (uint8_t *)data, sizeof(uint32_t)); + if (!result) { + return result; + } + *data = ntohl(*data); + return true; +} + +static bool read_multiple_bytes(const int socket, uint8_t *buffer, + uint32_t *bytes_received, + uint32_t max_buffer_length) +{ + uint32_t length; + bool result; + + result = read_data32(socket, &length); + if (!result) { + return result; + } + + if (length > max_buffer_length) { + return false; + } + + if (bytes_received) { + *bytes_received = length; + } + + if (length == 0) { + return true; + } + + return read_bytes(socket, buffer, length); +} + +static bool receive_platform_data(const int socket, + uint32_t transport_type, + uint32_t *command, + uint8_t *receive_buffer, + uint32_t *bytes_to_receive) +{ + bool result; + uint32_t response; + uint32_t bytes_received; + + result = read_data32(socket, &response); + if (!result) { + return result; + } + *command = response; + + result = read_data32(socket, &transport_type); + if (!result) { + return result; + } + + bytes_received = 0; + result = read_multiple_bytes(socket, receive_buffer, &bytes_received, + *bytes_to_receive); + if (!result) { + return result; + } + *bytes_to_receive = bytes_received; + + return result; +} + +static bool write_bytes(const int socket, const uint8_t *buffer, + uint32_t number_of_bytes) +{ + ssize_t number_sent = 0; + ssize_t result; + + while (number_sent < number_of_bytes) { + result = send(socket, buffer + number_sent, + number_of_bytes - number_sent, 0); + if (result == -1) { + return false; + } + number_sent += result; + } + return true; +} + +static bool write_data32(const int socket, uint32_t data) +{ + data = htonl(data); + return write_bytes(socket, (uint8_t *)&data, sizeof(uint32_t)); +} + +static bool write_multiple_bytes(const int socket, const uint8_t *buffer, + uint32_t bytes_to_send) +{ + bool result; + + result = write_data32(socket, bytes_to_send); + if (!result) { + return result; + } + + return write_bytes(socket, buffer, bytes_to_send); +} + +static bool send_platform_data(const int socket, + uint32_t transport_type, uint32_t command, + const uint8_t *send_buffer, size_t bytes_to_send) +{ + bool result; + + result = write_data32(socket, command); + if (!result) { + return result; + } + + result = write_data32(socket, transport_type); + if (!result) { + return result; + } + + return write_multiple_bytes(socket, send_buffer, bytes_to_send); +} + +int spdm_socket_connect(uint16_t port, Error **errp) +{ + int client_socket; + struct sockaddr_in server_addr; + + client_socket = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + if (client_socket < 0) { + error_setg(errp, "cannot create socket: %s", strerror(errno)); + return -1; + } + + memset((char *)&server_addr, 0, sizeof(server_addr)); + server_addr.sin_family = AF_INET; + server_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + server_addr.sin_port = htons(port); + + + if (connect(client_socket, (struct sockaddr *)&server_addr, + sizeof(server_addr)) < 0) { + error_setg(errp, "cannot connect: %s", strerror(errno)); + close(client_socket); + return -1; + } + + return client_socket; +} + +uint32_t spdm_socket_rsp(const int socket, uint32_t transport_type, + void *req, uint32_t req_len, + void *rsp, uint32_t rsp_len) +{ + uint32_t command; + bool result; + + result = send_platform_data(socket, transport_type, + SPDM_SOCKET_COMMAND_NORMAL, + req, req_len); + if (!result) { + return 0; + } + + result = receive_platform_data(socket, transport_type, &command, + (uint8_t *)rsp, &rsp_len); + if (!result) { + return 0; + } + + assert(command != 0); + + return rsp_len; +} + +void spdm_socket_close(const int socket, uint32_t transport_type) +{ + send_platform_data(socket, transport_type, + SPDM_SOCKET_COMMAND_SHUTDOWN, NULL, 0); +} diff --git a/chardev/char-win-stdio.c b/chardev/char-win-stdio.c index 1a18999e78..13325ca967 100644 --- a/chardev/char-win-stdio.c +++ b/chardev/char-win-stdio.c @@ -33,6 +33,7 @@ struct WinStdioChardev { Chardev parent; HANDLE hStdIn; + DWORD dwOldMode; HANDLE hInputReadyEvent; HANDLE hInputDoneEvent; HANDLE hInputThread; @@ -159,6 +160,7 @@ static void qemu_chr_open_stdio(Chardev *chr, } is_console = GetConsoleMode(stdio->hStdIn, &dwMode) != 0; + stdio->dwOldMode = dwMode; if (is_console) { if (qemu_add_wait_object(stdio->hStdIn, @@ -221,6 +223,9 @@ static void char_win_stdio_finalize(Object *obj) { WinStdioChardev *stdio = WIN_STDIO_CHARDEV(obj); + if (stdio->hStdIn != INVALID_HANDLE_VALUE) { + SetConsoleMode(stdio->hStdIn, stdio->dwOldMode); + } if (stdio->hInputReadyEvent != INVALID_HANDLE_VALUE) { CloseHandle(stdio->hInputReadyEvent); } diff --git a/contrib/plugins/Makefile b/contrib/plugins/Makefile index 449ead1130..98a89d5c40 100644 --- a/contrib/plugins/Makefile +++ b/contrib/plugins/Makefile @@ -28,6 +28,7 @@ NAMES += hwprofile NAMES += cache NAMES += drcov NAMES += ips +NAMES += stoptrigger ifeq ($(CONFIG_WIN32),y) SO_SUFFIX := .dll diff --git a/contrib/plugins/execlog.c b/contrib/plugins/execlog.c index 371db97eb1..1c1601cc0b 100644 --- a/contrib/plugins/execlog.c +++ b/contrib/plugins/execlog.c @@ -101,7 +101,7 @@ static void insn_check_regs(CPU *cpu) GByteArray *temp = reg->last; g_string_append_printf(cpu->last_exec, ", %s -> 0x", reg->name); /* TODO: handle BE properly */ - for (int i = sz; i >= 0; i--) { + for (int i = sz - 1; i >= 0; i--) { g_string_append_printf(cpu->last_exec, "%02x", reg->new->data[i]); } diff --git a/contrib/plugins/stoptrigger.c b/contrib/plugins/stoptrigger.c new file mode 100644 index 0000000000..03ee22f4c6 --- /dev/null +++ b/contrib/plugins/stoptrigger.c @@ -0,0 +1,151 @@ +/* + * Copyright (C) 2024, Simon Hamelin <simon.hamelin@grenoble-inp.org> + * + * Stop execution once a given address is reached or if the + * count of executed instructions reached a specified limit + * + * License: GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include <assert.h> +#include <glib.h> +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> + +#include <qemu-plugin.h> + +QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION; + +/* Scoreboard to track executed instructions count */ +typedef struct { + uint64_t insn_count; +} InstructionsCount; +static struct qemu_plugin_scoreboard *insn_count_sb; +static qemu_plugin_u64 insn_count; + +static uint64_t icount; +static int icount_exit_code; + +static bool exit_on_icount; +static bool exit_on_address; + +/* Map trigger addresses to exit code */ +static GHashTable *addrs_ht; + +static void exit_emulation(int return_code, char *message) +{ + qemu_plugin_outs(message); + g_free(message); + exit(return_code); +} + +static void exit_icount_reached(unsigned int cpu_index, void *udata) +{ + uint64_t insn_vaddr = GPOINTER_TO_UINT(udata); + char *msg = g_strdup_printf("icount reached at 0x%" PRIx64 ", exiting\n", + insn_vaddr); + + exit_emulation(icount_exit_code, msg); +} + +static void exit_address_reached(unsigned int cpu_index, void *udata) +{ + uint64_t insn_vaddr = GPOINTER_TO_UINT(udata); + char *msg = g_strdup_printf("0x%" PRIx64 " reached, exiting\n", insn_vaddr); + int exit_code; + + exit_code = GPOINTER_TO_INT( + g_hash_table_lookup(addrs_ht, GUINT_TO_POINTER(insn_vaddr))); + + exit_emulation(exit_code, msg); +} + +static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb) +{ + size_t tb_n = qemu_plugin_tb_n_insns(tb); + for (size_t i = 0; i < tb_n; i++) { + struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i); + gpointer insn_vaddr = GUINT_TO_POINTER(qemu_plugin_insn_vaddr(insn)); + + if (exit_on_icount) { + /* Increment and check scoreboard for each instruction */ + qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu( + insn, QEMU_PLUGIN_INLINE_ADD_U64, insn_count, 1); + qemu_plugin_register_vcpu_insn_exec_cond_cb( + insn, exit_icount_reached, QEMU_PLUGIN_CB_NO_REGS, + QEMU_PLUGIN_COND_EQ, insn_count, icount + 1, insn_vaddr); + } + + if (exit_on_address) { + if (g_hash_table_contains(addrs_ht, insn_vaddr)) { + /* Exit triggered by address */ + qemu_plugin_register_vcpu_insn_exec_cb( + insn, exit_address_reached, QEMU_PLUGIN_CB_NO_REGS, + insn_vaddr); + } + } + } +} + +static void plugin_exit(qemu_plugin_id_t id, void *p) +{ + g_hash_table_destroy(addrs_ht); + qemu_plugin_scoreboard_free(insn_count_sb); +} + +QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id, + const qemu_info_t *info, int argc, + char **argv) +{ + addrs_ht = g_hash_table_new(NULL, g_direct_equal); + + insn_count_sb = qemu_plugin_scoreboard_new(sizeof(InstructionsCount)); + insn_count = qemu_plugin_scoreboard_u64_in_struct( + insn_count_sb, InstructionsCount, insn_count); + + for (int i = 0; i < argc; i++) { + char *opt = argv[i]; + g_auto(GStrv) tokens = g_strsplit(opt, "=", 2); + if (g_strcmp0(tokens[0], "icount") == 0) { + g_auto(GStrv) icount_tokens = g_strsplit(tokens[1], ":", 2); + icount = g_ascii_strtoull(icount_tokens[0], NULL, 0); + if (icount < 1 || g_strrstr(icount_tokens[0], "-") != NULL) { + fprintf(stderr, + "icount parsing failed: '%s' must be a positive " + "integer\n", + icount_tokens[0]); + return -1; + } + if (icount_tokens[1]) { + icount_exit_code = g_ascii_strtoull(icount_tokens[1], NULL, 0); + } + exit_on_icount = true; + } else if (g_strcmp0(tokens[0], "addr") == 0) { + g_auto(GStrv) addr_tokens = g_strsplit(tokens[1], ":", 2); + uint64_t exit_addr = g_ascii_strtoull(addr_tokens[0], NULL, 0); + int exit_code = 0; + if (addr_tokens[1]) { + exit_code = g_ascii_strtoull(addr_tokens[1], NULL, 0); + } + g_hash_table_insert(addrs_ht, GUINT_TO_POINTER(exit_addr), + GINT_TO_POINTER(exit_code)); + exit_on_address = true; + } else { + fprintf(stderr, "option parsing failed: %s\n", opt); + return -1; + } + } + + if (!exit_on_icount && !exit_on_address) { + fprintf(stderr, "'icount' or 'addr' argument missing\n"); + return -1; + } + + /* Register translation block and exit callbacks */ + qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans); + qemu_plugin_register_atexit_cb(id, plugin_exit, NULL); + + return 0; +} diff --git a/contrib/vhost-user-blk/vhost-user-blk.c b/contrib/vhost-user-blk/vhost-user-blk.c index 9492146855..6cc18a1c04 100644 --- a/contrib/vhost-user-blk/vhost-user-blk.c +++ b/contrib/vhost-user-blk/vhost-user-blk.c @@ -196,7 +196,7 @@ vub_discard_write_zeroes(VubReq *req, struct iovec *iov, uint32_t iovcnt, VubDev *vdev_blk = req->vdev_blk; desc = buf; uint64_t range[2] = { le64_to_cpu(desc->sector) << 9, - le32_to_cpu(desc->num_sectors) << 9 }; + (uint64_t)le32_to_cpu(desc->num_sectors) << 9 }; if (type == VIRTIO_BLK_T_DISCARD) { if (ioctl(vdev_blk->blk_fd, BLKDISCARD, range) == 0) { g_free(buf); diff --git a/docs/devel/tcg-plugins.rst b/docs/devel/tcg-plugins.rst index f7d7b9e3a4..954623f9bf 100644 --- a/docs/devel/tcg-plugins.rst +++ b/docs/devel/tcg-plugins.rst @@ -642,6 +642,28 @@ The plugin has a number of arguments, all of them are optional: configuration arguments implies ``l2=on``. (default: N = 2097152 (2MB), B = 64, A = 16) +- contrib/plugins/stoptrigger.c + +The stoptrigger plugin allows to setup triggers to stop emulation. +It can be used for research purposes to launch some code and precisely stop it +and understand where its execution flow went. + +Two types of triggers can be configured: a count of instructions to stop at, +or an address to stop at. Multiple triggers can be set at once. + +By default, QEMU will exit with return code 0. A custom return code can be +configured for each trigger using ``:CODE`` syntax. + +For example, to stop at the 20-th instruction with return code 41, at address +0xd4 with return code 0 or at address 0xd8 with return code 42:: + + $ qemu-system-aarch64 $(QEMU_ARGS) \ + -plugin ./contrib/plugins/libstoptrigger.so,icount=20:41,addr=0xd4,addr=0xd8:42 -d plugin + +The plugin will log the reason of exit, for example:: + + 0xd4 reached, exiting + Plugin API ========== diff --git a/docs/interop/qemu-ga.rst b/docs/interop/qemu-ga.rst index 72fb75a6f5..9c7380896a 100644 --- a/docs/interop/qemu-ga.rst +++ b/docs/interop/qemu-ga.rst @@ -28,11 +28,30 @@ configuration options on the command line. For the same key, the last option wins, but the lists accumulate (see below for configuration file format). +If an allowed RPCs list is defined in the configuration, then all +RPCs will be blocked by default, except for the allowed list. + +If a blocked RPCs list is defined in the configuration, then all +RPCs will be allowed by default, except for the blocked list. + +If both allowed and blocked RPCs lists are defined in the configuration, +then all RPCs will be blocked by default, then the allowed list will +be applied, followed by the blocked list. + +While filesystems are frozen, all except for a designated safe set +of RPCs will blocked, regardless of what the general configuration +declares. + Options ------- .. program:: qemu-ga +.. option:: -c, --config=PATH + + Configuration file path (the default is |CONFDIR|\ ``/qemu-ga.conf``, + unless overriden by the QGA_CONF environment variable) + .. option:: -m, --method=METHOD Transport method: one of ``unix-listen``, ``virtio-serial``, or @@ -131,6 +150,7 @@ fsfreeze-hook string statedir string verbose boolean block-rpcs string list +allow-rpcs string list ============= =========== See also diff --git a/docs/specs/acpi_hw_reduced_hotplug.rst b/docs/specs/acpi_hw_reduced_hotplug.rst index 0bd3f9399f..3acd6fcd8b 100644 --- a/docs/specs/acpi_hw_reduced_hotplug.rst +++ b/docs/specs/acpi_hw_reduced_hotplug.rst @@ -64,7 +64,8 @@ GED IO interface (4 byte access) 0: Memory hotplug event 1: System power down event 2: NVDIMM hotplug event - 3-31: Reserved + 3: CPU hotplug event + 4-31: Reserved **write_access:** diff --git a/docs/specs/index.rst b/docs/specs/index.rst index e738ea7d10..be899b49c2 100644 --- a/docs/specs/index.rst +++ b/docs/specs/index.rst @@ -29,6 +29,7 @@ guest hardware that is specific to QEMU. edu ivshmem-spec pvpanic + spdm standard-vga virt-ctlr vmcoreinfo diff --git a/docs/specs/spdm.rst b/docs/specs/spdm.rst new file mode 100644 index 0000000000..f7de080ff0 --- /dev/null +++ b/docs/specs/spdm.rst @@ -0,0 +1,134 @@ +====================================================== +QEMU Security Protocols and Data Models (SPDM) Support +====================================================== + +SPDM enables authentication, attestation and key exchange to assist in +providing infrastructure security enablement. It's a standard published +by the `DMTF`_. + +QEMU supports connecting to a SPDM responder implementation. This allows an +external application to emulate the SPDM responder logic for an SPDM device. + +Setting up a SPDM server +======================== + +When using QEMU with SPDM devices QEMU will connect to a server which +implements the SPDM functionality. + +SPDM-Utils +---------- + +You can use `SPDM Utils`_ to emulate a responder. This is the simplest method. + +SPDM-Utils is a Linux applications to manage, test and develop devices +supporting DMTF Security Protocol and Data Model (SPDM). It is written in Rust +and utilises libspdm. + +To use SPDM-Utils you will need to do the following steps. Details are included +in the SPDM-Utils README. + + 1. `Build libspdm`_ + 2. `Build SPDM Utils`_ + 3. `Run it as a server`_ + +spdm-emu +-------- + +You can use `spdm emu`_ to model the +SPDM responder. + +.. code-block:: shell + + $ cd spdm-emu + $ git submodule init; git submodule update --recursive + $ mkdir build; cd build + $ cmake -DARCH=x64 -DTOOLCHAIN=GCC -DTARGET=Debug -DCRYPTO=openssl .. + $ make -j32 + $ make copy_sample_key # Build certificates, required for SPDM authentication. + +It is worth noting that the certificates should be in compliance with +PCIe r6.1 sec 6.31.3. This means you will need to add the following to +openssl.cnf + +.. code-block:: + + subjectAltName = otherName:2.23.147;UTF8:Vendor=1b36:Device=0010:CC=010802:REV=02:SSVID=1af4:SSID=1100 + 2.23.147 = ASN1:OID:2.23.147 + +and then manually regenerate some certificates with: + +.. code-block:: shell + + $ openssl req -nodes -newkey ec:param.pem -keyout end_responder.key \ + -out end_responder.req -sha384 -batch \ + -subj "/CN=DMTF libspdm ECP384 responder cert" + + $ openssl x509 -req -in end_responder.req -out end_responder.cert \ + -CA inter.cert -CAkey inter.key -sha384 -days 3650 -set_serial 3 \ + -extensions v3_end -extfile ../openssl.cnf + + $ openssl asn1parse -in end_responder.cert -out end_responder.cert.der + + $ cat ca.cert.der inter.cert.der end_responder.cert.der > bundle_responder.certchain.der + +You can use SPDM-Utils instead as it will generate the correct certificates +automatically. + +The responder can then be launched with + +.. code-block:: shell + + $ cd bin + $ ./spdm_responder_emu --trans PCI_DOE + +Connecting an SPDM NVMe device +============================== + +Once a SPDM server is running we can start QEMU and connect to the server. + +For an NVMe device first let's setup a block we can use + +.. code-block:: shell + + $ cd qemu-spdm/linux/image + $ dd if=/dev/zero of=blknvme bs=1M count=2096 # 2GB NNMe Drive + +Then you can add this to your QEMU command line: + +.. code-block:: shell + + -drive file=blknvme,if=none,id=mynvme,format=raw \ + -device nvme,drive=mynvme,serial=deadbeef,spdm_port=2323 + +At which point QEMU will try to connect to the SPDM server. + +Note that if using x64-64 you will want to use the q35 machine instead +of the default. So the entire QEMU command might look like this + +.. code-block:: shell + + qemu-system-x86_64 -M q35 \ + --kernel bzImage \ + -drive file=rootfs.ext2,if=virtio,format=raw \ + -append "root=/dev/vda console=ttyS0" \ + -net none -nographic \ + -drive file=blknvme,if=none,id=mynvme,format=raw \ + -device nvme,drive=mynvme,serial=deadbeef,spdm_port=2323 + +.. _DMTF: + https://www.dmtf.org/standards/SPDM + +.. _SPDM Utils: + https://github.com/westerndigitalcorporation/spdm-utils + +.. _spdm emu: + https://github.com/dmtf/spdm-emu + +.. _Build libspdm: + https://github.com/westerndigitalcorporation/spdm-utils?tab=readme-ov-file#build-libspdm + +.. _Build SPDM Utils: + https://github.com/westerndigitalcorporation/spdm-utils?tab=readme-ov-file#build-the-binary + +.. _Run it as a server: + https://github.com/westerndigitalcorporation/spdm-utils#qemu-spdm-device-emulation diff --git a/docs/system/index.rst b/docs/system/index.rst index c21065e519..718e9d3c56 100644 --- a/docs/system/index.rst +++ b/docs/system/index.rst @@ -39,3 +39,4 @@ or Hypervisor.Framework. multi-process confidential-guest-support vm-templating + sriov diff --git a/docs/system/sriov.rst b/docs/system/sriov.rst new file mode 100644 index 0000000000..a851a66a4b --- /dev/null +++ b/docs/system/sriov.rst @@ -0,0 +1,36 @@ +.. SPDX-License-Identifier: GPL-2.0-or-later + +Compsable SR-IOV device +======================= + +SR-IOV (Single Root I/O Virtualization) is an optional extended capability of a +PCI Express device. It allows a single physical function (PF) to appear as +multiple virtual functions (VFs) for the main purpose of eliminating software +overhead in I/O from virtual machines. + +There are devices with predefined SR-IOV configurations, but it is also possible +to compose an SR-IOV device yourself. Composing an SR-IOV device is currently +only supported by virtio-net-pci. + +Users can configure an SR-IOV-capable virtio-net device by adding +virtio-net-pci functions to a bus. Below is a command line example: + +.. code-block:: shell + + -netdev user,id=n -netdev user,id=o + -netdev user,id=p -netdev user,id=q + -device pcie-root-port,id=b + -device virtio-net-pci,bus=b,addr=0x0.0x3,netdev=q,sriov-pf=f + -device virtio-net-pci,bus=b,addr=0x0.0x2,netdev=p,sriov-pf=f + -device virtio-net-pci,bus=b,addr=0x0.0x1,netdev=o,sriov-pf=f + -device virtio-net-pci,bus=b,addr=0x0.0x0,netdev=n,id=f + +The VFs specify the paired PF with ``sriov-pf`` property. The PF must be +added after all VFs. It is the user's responsibility to ensure that VFs have +function numbers larger than one of the PF, and that the function numbers +have a consistent stride. + +You may also need to perform additional steps to activate the SR-IOV feature on +your guest. For Linux, refer to [1]_. + +.. [1] https://docs.kernel.org/PCI/pci-iov-howto.html diff --git a/gdbstub/gdbstub.c b/gdbstub/gdbstub.c index b9ad0a063e..d08568cea0 100644 --- a/gdbstub/gdbstub.c +++ b/gdbstub/gdbstub.c @@ -618,6 +618,19 @@ void gdb_register_coprocessor(CPUState *cpu, } } +void gdb_unregister_coprocessor_all(CPUState *cpu) +{ + /* + * Safe to nuke everything. GDBRegisterState::xml is static const char so + * it won't be freed + */ + g_array_free(cpu->gdb_regs, true); + + cpu->gdb_regs = NULL; + cpu->gdb_num_regs = 0; + cpu->gdb_num_g_regs = 0; +} + static void gdb_process_breakpoint_remove_all(GDBProcess *p) { CPUState *cpu = gdb_get_first_cpu_in_process(p); @@ -1614,18 +1627,21 @@ static void handle_query_thread_extra(GArray *params, void *user_ctx) gdb_put_strbuf(); } -static char *extended_qsupported_features; -void gdb_extend_qsupported_features(char *qsupported_features) -{ - /* - * We don't support different sets of CPU gdb features on different CPUs yet - * so assert the feature strings are the same on all CPUs, or is set only - * once (1 CPU). - */ - g_assert(extended_qsupported_features == NULL || - g_strcmp0(extended_qsupported_features, qsupported_features) == 0); - extended_qsupported_features = qsupported_features; +static char **extra_query_flags; + +void gdb_extend_qsupported_features(char *qflags) +{ + if (!extra_query_flags) { + extra_query_flags = g_new0(char *, 2); + extra_query_flags[0] = g_strdup(qflags); + } else if (!g_strv_contains((const gchar * const *) extra_query_flags, + qflags)) { + int len = g_strv_length(extra_query_flags); + extra_query_flags = g_realloc_n(extra_query_flags, len + 2, + sizeof(char *)); + extra_query_flags[len] = g_strdup(qflags); + } } static void handle_query_supported(GArray *params, void *user_ctx) @@ -1668,8 +1684,11 @@ static void handle_query_supported(GArray *params, void *user_ctx) g_string_append(gdbserver_state.str_buf, ";vContSupported+;multiprocess+"); - if (extended_qsupported_features) { - g_string_append(gdbserver_state.str_buf, extended_qsupported_features); + if (extra_query_flags) { + int extras = g_strv_length(extra_query_flags); + for (int i = 0; i < extras; i++) { + g_string_append(gdbserver_state.str_buf, extra_query_flags[i]); + } } gdb_put_strbuf(); @@ -1753,39 +1772,58 @@ static const GdbCmdParseEntry gdb_gen_query_set_common_table[] = { }, }; -/* Compares if a set of command parsers is equal to another set of parsers. */ -static bool cmp_cmds(GdbCmdParseEntry *c, GdbCmdParseEntry *d, int size) +/** + * extend_table() - extend one of the command tables + * @table: the command table to extend (or NULL) + * @extensions: a list of GdbCmdParseEntry pointers + * + * The entries themselves should be pointers to static const + * GdbCmdParseEntry entries. If the entry is already in the table we + * skip adding it again. + * + * Returns (a potentially freshly allocated) GPtrArray of GdbCmdParseEntry + */ +static GPtrArray *extend_table(GPtrArray *table, GPtrArray *extensions) { - for (int i = 0; i < size; i++) { - if (!(c[i].handler == d[i].handler && - g_strcmp0(c[i].cmd, d[i].cmd) == 0 && - c[i].cmd_startswith == d[i].cmd_startswith && - g_strcmp0(c[i].schema, d[i].schema) == 0)) { + if (!table) { + table = g_ptr_array_new(); + } - /* Sets are different. */ - return false; + for (int i = 0; i < extensions->len; i++) { + gpointer entry = g_ptr_array_index(extensions, i); + if (!g_ptr_array_find(table, entry, NULL)) { + g_ptr_array_add(table, entry); } } - /* Sets are equal, i.e. contain the same command parsers. */ - return true; + return table; } -static GdbCmdParseEntry *extended_query_table; -static int extended_query_table_size; -void gdb_extend_query_table(GdbCmdParseEntry *table, int size) +/** + * process_extended_table() - run through an extended command table + * @table: the command table to check + * @data: parameters + * + * returns true if the command was found and executed + */ +static bool process_extended_table(GPtrArray *table, const char *data) { - /* - * We don't support different sets of CPU gdb features on different CPUs yet - * so assert query table is the same on all CPUs, or is set only once - * (1 CPU). - */ - g_assert(extended_query_table == NULL || - (extended_query_table_size == size && - cmp_cmds(extended_query_table, table, size))); + for (int i = 0; i < table->len; i++) { + const GdbCmdParseEntry *entry = g_ptr_array_index(table, i); + if (process_string_cmd(data, entry, 1)) { + return true; + } + } + return false; +} + + +/* Ptr to GdbCmdParseEntry */ +static GPtrArray *extended_query_table; - extended_query_table = table; - extended_query_table_size = size; +void gdb_extend_query_table(GPtrArray *new_queries) +{ + extended_query_table = extend_table(extended_query_table, new_queries); } static const GdbCmdParseEntry gdb_gen_query_table[] = { @@ -1880,20 +1918,12 @@ static const GdbCmdParseEntry gdb_gen_query_table[] = { #endif }; -static GdbCmdParseEntry *extended_set_table; -static int extended_set_table_size; -void gdb_extend_set_table(GdbCmdParseEntry *table, int size) -{ - /* - * We don't support different sets of CPU gdb features on different CPUs yet - * so assert set table is the same on all CPUs, or is set only once (1 CPU). - */ - g_assert(extended_set_table == NULL || - (extended_set_table_size == size && - cmp_cmds(extended_set_table, table, size))); +/* Ptr to GdbCmdParseEntry */ +static GPtrArray *extended_set_table; - extended_set_table = table; - extended_set_table_size = size; +void gdb_extend_set_table(GPtrArray *new_set) +{ + extended_set_table = extend_table(extended_set_table, new_set); } static const GdbCmdParseEntry gdb_gen_set_table[] = { @@ -1924,26 +1954,28 @@ static const GdbCmdParseEntry gdb_gen_set_table[] = { static void handle_gen_query(GArray *params, void *user_ctx) { + const char *data; + if (!params->len) { return; } - if (process_string_cmd(gdb_get_cmd_param(params, 0)->data, + data = gdb_get_cmd_param(params, 0)->data; + + if (process_string_cmd(data, gdb_gen_query_set_common_table, ARRAY_SIZE(gdb_gen_query_set_common_table))) { return; } - if (process_string_cmd(gdb_get_cmd_param(params, 0)->data, + if (process_string_cmd(data, gdb_gen_query_table, ARRAY_SIZE(gdb_gen_query_table))) { return; } if (extended_query_table && - process_string_cmd(gdb_get_cmd_param(params, 0)->data, - extended_query_table, - extended_query_table_size)) { + process_extended_table(extended_query_table, data)) { return; } @@ -1953,26 +1985,28 @@ static void handle_gen_query(GArray *params, void *user_ctx) static void handle_gen_set(GArray *params, void *user_ctx) { + const char *data; + if (!params->len) { return; } - if (process_string_cmd(gdb_get_cmd_param(params, 0)->data, + data = gdb_get_cmd_param(params, 0)->data; + + if (process_string_cmd(data, gdb_gen_query_set_common_table, ARRAY_SIZE(gdb_gen_query_set_common_table))) { return; } - if (process_string_cmd(gdb_get_cmd_param(params, 0)->data, + if (process_string_cmd(data, gdb_gen_set_table, ARRAY_SIZE(gdb_gen_set_table))) { return; } if (extended_set_table && - process_string_cmd(gdb_get_cmd_param(params, 0)->data, - extended_set_table, - extended_set_table_size)) { + process_extended_table(extended_set_table, data)) { return; } diff --git a/hw/acpi/acpi-cpu-hotplug-stub.c b/hw/acpi/acpi-cpu-hotplug-stub.c index 3fc4b14c26..c6c61bb9cd 100644 --- a/hw/acpi/acpi-cpu-hotplug-stub.c +++ b/hw/acpi/acpi-cpu-hotplug-stub.c @@ -19,6 +19,12 @@ void legacy_acpi_cpu_hotplug_init(MemoryRegion *parent, Object *owner, return; } +void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner, + CPUHotplugState *state, hwaddr base_addr) +{ + return; +} + void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list) { return; diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index 2d81c1e790..5cb60ca8bc 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -7,7 +7,6 @@ #include "trace.h" #include "sysemu/numa.h" -#define ACPI_CPU_HOTPLUG_REG_LEN 12 #define ACPI_CPU_SELECTOR_OFFSET_WR 0 #define ACPI_CPU_FLAGS_OFFSET_RW 4 #define ACPI_CPU_CMD_OFFSET_WR 5 @@ -339,9 +338,10 @@ const VMStateDescription vmstate_cpu_hotplug = { #define CPU_FW_EJECT_EVENT "CEJF" void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, - build_madt_cpu_fn build_madt_cpu, hwaddr io_base, + build_madt_cpu_fn build_madt_cpu, hwaddr base_addr, const char *res_root, - const char *event_handler_method) + const char *event_handler_method, + AmlRegionSpace rs) { Aml *ifctx; Aml *field; @@ -365,14 +365,22 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, aml_name_decl("_UID", aml_string("CPU Hotplug resources"))); aml_append(cpu_ctrl_dev, aml_mutex(CPU_LOCK, 0)); + assert((rs == AML_SYSTEM_IO) || (rs == AML_SYSTEM_MEMORY)); + crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, io_base, io_base, 1, + if (rs == AML_SYSTEM_IO) { + aml_append(crs, aml_io(AML_DECODE16, base_addr, base_addr, 1, ACPI_CPU_HOTPLUG_REG_LEN)); + } else if (rs == AML_SYSTEM_MEMORY) { + aml_append(crs, aml_memory32_fixed(base_addr, + ACPI_CPU_HOTPLUG_REG_LEN, AML_READ_WRITE)); + } + aml_append(cpu_ctrl_dev, aml_name_decl("_CRS", crs)); /* declare CPU hotplug MMIO region with related access fields */ aml_append(cpu_ctrl_dev, - aml_operation_region("PRST", AML_SYSTEM_IO, aml_int(io_base), + aml_operation_region("PRST", rs, aml_int(base_addr), ACPI_CPU_HOTPLUG_REG_LEN)); field = aml_field("PRST", AML_BYTE_ACC, AML_NOLOCK, diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index 2d6e91b124..15b4c3ebbf 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -25,6 +25,7 @@ static const uint32_t ged_supported_events[] = { ACPI_GED_MEM_HOTPLUG_EVT, ACPI_GED_PWR_DOWN_EVT, ACPI_GED_NVDIMM_HOTPLUG_EVT, + ACPI_GED_CPU_HOTPLUG_EVT, }; /* @@ -107,6 +108,9 @@ void build_ged_aml(Aml *table, const char *name, HotplugHandler *hotplug_dev, aml_append(if_ctx, aml_call0(MEMORY_DEVICES_CONTAINER "." MEMORY_SLOT_SCAN_METHOD)); break; + case ACPI_GED_CPU_HOTPLUG_EVT: + aml_append(if_ctx, aml_call0(AML_GED_EVT_CPU_SCAN_METHOD)); + break; case ACPI_GED_PWR_DOWN_EVT: aml_append(if_ctx, aml_notify(aml_name(ACPI_POWER_BUTTON_DEVICE), @@ -234,6 +238,8 @@ static void acpi_ged_device_plug_cb(HotplugHandler *hotplug_dev, } else { acpi_memory_plug_cb(hotplug_dev, &s->memhp_state, dev, errp); } + } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { + acpi_cpu_plug_cb(hotplug_dev, &s->cpuhp_state, dev, errp); } else { error_setg(errp, "virt: device plug request for unsupported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -248,6 +254,8 @@ static void acpi_ged_unplug_request_cb(HotplugHandler *hotplug_dev, if ((object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) && !(object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM)))) { acpi_memory_unplug_request_cb(hotplug_dev, &s->memhp_state, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { + acpi_cpu_unplug_request_cb(hotplug_dev, &s->cpuhp_state, dev, errp); } else { error_setg(errp, "acpi: device unplug request for unsupported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -261,6 +269,8 @@ static void acpi_ged_unplug_cb(HotplugHandler *hotplug_dev, if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { acpi_memory_unplug_cb(&s->memhp_state, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { + acpi_cpu_unplug_cb(&s->cpuhp_state, dev, errp); } else { error_setg(errp, "acpi: device unplug for unsupported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -272,6 +282,7 @@ static void acpi_ged_ospm_status(AcpiDeviceIf *adev, ACPIOSTInfoList ***list) AcpiGedState *s = ACPI_GED(adev); acpi_memory_ospm_status(&s->memhp_state, list); + acpi_cpu_ospm_status(&s->cpuhp_state, list); } static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev) @@ -286,6 +297,8 @@ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev) sel = ACPI_GED_PWR_DOWN_EVT; } else if (ev & ACPI_NVDIMM_HOTPLUG_STATUS) { sel = ACPI_GED_NVDIMM_HOTPLUG_EVT; + } else if (ev & ACPI_CPU_HOTPLUG_STATUS) { + sel = ACPI_GED_CPU_HOTPLUG_EVT; } else { /* Unknown event. Return without generating interrupt. */ warn_report("GED: Unsupported event %d. No irq injected", ev); @@ -371,6 +384,42 @@ static const VMStateDescription vmstate_acpi_ged = { } }; +static void acpi_ged_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + AcpiGedState *s = ACPI_GED(dev); + uint32_t ged_events; + int i; + + ged_events = ctpop32(s->ged_event_bitmap); + + for (i = 0; i < ARRAY_SIZE(ged_supported_events) && ged_events; i++) { + uint32_t event = s->ged_event_bitmap & ged_supported_events[i]; + + if (!event) { + continue; + } + + switch (event) { + case ACPI_GED_CPU_HOTPLUG_EVT: + /* initialize CPU Hotplug related regions */ + memory_region_init(&s->container_cpuhp, OBJECT(dev), + "cpuhp container", + ACPI_CPU_HOTPLUG_REG_LEN); + sysbus_init_mmio(sbd, &s->container_cpuhp); + cpu_hotplug_hw_init(&s->container_cpuhp, OBJECT(dev), + &s->cpuhp_state, 0); + break; + } + ged_events--; + } + + if (ged_events) { + error_report("Unsupported events specified"); + abort(); + } +} + static void acpi_ged_initfn(Object *obj) { DeviceState *dev = DEVICE(obj); @@ -411,6 +460,7 @@ static void acpi_ged_class_init(ObjectClass *class, void *data) dc->desc = "ACPI Generic Event Device"; device_class_set_props(dc, acpi_ged_properties); dc->vmsd = &vmstate_acpi_ged; + dc->realize = acpi_ged_realize; hc->plug = acpi_ged_device_plug_cb; hc->unplug_request = acpi_ged_unplug_request_cb; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index b0c68d66a3..719e83e6a1 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -3308,6 +3308,7 @@ DEFINE_VIRT_MACHINE_AS_LATEST(9, 1) static void virt_machine_9_0_options(MachineClass *mc) { virt_machine_9_1_options(mc); + mc->smbios_memory_device_size = 16 * GiB; compat_props_add(mc->compat_props, hw_compat_9_0, hw_compat_9_0_len); } DEFINE_VIRT_MACHINE(9, 0) diff --git a/hw/audio/virtio-snd.c b/hw/audio/virtio-snd.c index 5993f4f040..e5196aa4bb 100644 --- a/hw/audio/virtio-snd.c +++ b/hw/audio/virtio-snd.c @@ -282,11 +282,13 @@ uint32_t virtio_snd_set_pcm_params(VirtIOSound *s, error_report("Number of channels is not supported."); return cpu_to_le32(VIRTIO_SND_S_NOT_SUPP); } - if (!(supported_formats & BIT(params->format))) { + if (BIT(params->format) > sizeof(supported_formats) || + !(supported_formats & BIT(params->format))) { error_report("Stream format is not supported."); return cpu_to_le32(VIRTIO_SND_S_NOT_SUPP); } - if (!(supported_rates & BIT(params->rate))) { + if (BIT(params->rate) > sizeof(supported_rates) || + !(supported_rates & BIT(params->rate))) { error_report("Stream rate is not supported."); return cpu_to_le32(VIRTIO_SND_S_NOT_SUPP); } @@ -1261,7 +1263,7 @@ static void virtio_snd_pcm_in_cb(void *data, int available) { VirtIOSoundPCMStream *stream = data; VirtIOSoundPCMBuffer *buffer; - size_t size; + size_t size, max_size; WITH_QEMU_LOCK_GUARD(&stream->queue_mutex) { while (!QSIMPLEQ_EMPTY(&stream->queue)) { @@ -1275,7 +1277,12 @@ static void virtio_snd_pcm_in_cb(void *data, int available) continue; } + max_size = iov_size(buffer->elem->in_sg, buffer->elem->in_num); for (;;) { + if (buffer->size >= max_size) { + return_rx_buffer(stream, buffer); + break; + } size = AUD_read(stream->voice.in, buffer->data + buffer->size, MIN(available, (stream->params.period_bytes - diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c index fdbc30b9ce..5b7f46bbb0 100644 --- a/hw/block/vhost-user-blk.c +++ b/hw/block/vhost-user-blk.c @@ -51,6 +51,7 @@ static const int user_feature_bits[] = { VIRTIO_F_RING_PACKED, VIRTIO_F_IOMMU_PLATFORM, VIRTIO_F_RING_RESET, + VIRTIO_F_IN_ORDER, VIRTIO_F_NOTIFICATION_DATA, VHOST_INVALID_FEATURE_BIT }; diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c index d2e3e4570a..7982ecd39a 100644 --- a/hw/core/cpu-common.c +++ b/hw/core/cpu-common.c @@ -282,7 +282,10 @@ static void cpu_common_finalize(Object *obj) } #endif free_queued_cpu_work(cpu); - g_array_free(cpu->gdb_regs, TRUE); + /* If cleanup didn't happen in context to gdb_unregister_coprocessor_all */ + if (cpu->gdb_regs) { + g_array_free(cpu->gdb_regs, TRUE); + } qemu_lockcnt_destroy(&cpu->in_ioctl_lock); qemu_mutex_destroy(&cpu->work_mutex); qemu_cond_destroy(cpu->halt_cond); diff --git a/hw/core/machine.c b/hw/core/machine.c index bc38cad7f2..27dcda0248 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -36,7 +36,8 @@ GlobalProperty hw_compat_9_0[] = { {"arm-cpu", "backcompat-cntfrq", "true" }, - {"scsi-disk-base", "migrate-emulated-scsi-request", "false" }, + { "scsi-hd", "migrate-emulated-scsi-request", "false" }, + { "scsi-cd", "migrate-emulated-scsi-request", "false" }, {"vfio-pci", "skip-vsc-check", "false" }, { "virtio-pci", "x-pcie-pm-no-soft-reset", "off" }, {"sd-card", "spec_version", "2" }, @@ -1004,6 +1005,12 @@ static void machine_class_init(ObjectClass *oc, void *data) /* Default 128 MB as guest ram size */ mc->default_ram_size = 128 * MiB; mc->rom_file_has_mr = true; + /* + * SMBIOS 3.1.0 7.18.5 Memory Device — Extended Size + * use max possible value that could be encoded into + * 'Extended Size' field (2047Tb). + */ + mc->smbios_memory_device_size = 2047 * TiB; /* numa node memory size aligned on 8MB by default. * On Linux, each node's border has to be 8MB aligned diff --git a/hw/cxl/cxl-events.c b/hw/cxl/cxl-events.c index d397718b1b..12dee2e467 100644 --- a/hw/cxl/cxl-events.c +++ b/hw/cxl/cxl-events.c @@ -139,6 +139,19 @@ bool cxl_event_insert(CXLDeviceState *cxlds, CXLEventLogType log_type, return cxl_event_count(log) == 1; } +void cxl_discard_all_event_records(CXLDeviceState *cxlds) +{ + CXLEventLogType log_type; + CXLEventLog *log; + + for (log_type = 0; log_type < CXL_EVENT_TYPE_MAX; log_type++) { + log = &cxlds->event_logs[log_type]; + while (!cxl_event_empty(log)) { + cxl_event_delete_head(cxlds, log_type, log); + } + } +} + CXLRetCode cxl_event_get_records(CXLDeviceState *cxlds, CXLGetEventPayload *pl, uint8_t log_type, int max_recs, size_t *len) diff --git a/hw/cxl/cxl-host.c b/hw/cxl/cxl-host.c index c5f5fcfd64..e9f2543c43 100644 --- a/hw/cxl/cxl-host.c +++ b/hw/cxl/cxl-host.c @@ -315,7 +315,8 @@ static void machine_set_cxl(Object *obj, Visitor *v, const char *name, static void machine_get_cfmw(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { - CXLFixedMemoryWindowOptionsList **list = opaque; + CXLState *state = opaque; + CXLFixedMemoryWindowOptionsList **list = &state->cfmw_list; visit_type_CXLFixedMemoryWindowOptionsList(v, name, list, errp); } diff --git a/hw/cxl/cxl-mailbox-utils.c b/hw/cxl/cxl-mailbox-utils.c index 74eeb6fde7..b752920ec8 100644 --- a/hw/cxl/cxl-mailbox-utils.c +++ b/hw/cxl/cxl-mailbox-utils.c @@ -12,6 +12,7 @@ #include "hw/pci/msix.h" #include "hw/cxl/cxl.h" #include "hw/cxl/cxl_events.h" +#include "hw/cxl/cxl_mailbox.h" #include "hw/pci/pci.h" #include "hw/pci-bridge/cxl_upstream_port.h" #include "qemu/cutils.h" @@ -62,12 +63,18 @@ enum { #define SET_INTERRUPT_POLICY 0x3 FIRMWARE_UPDATE = 0x02, #define GET_INFO 0x0 + #define TRANSFER 0x1 + #define ACTIVATE 0x2 TIMESTAMP = 0x03, #define GET 0x0 #define SET 0x1 LOGS = 0x04, #define GET_SUPPORTED 0x0 #define GET_LOG 0x1 + FEATURES = 0x05, + #define GET_SUPPORTED 0x0 + #define GET_FEATURE 0x1 + #define SET_FEATURE 0x2 IDENTIFY = 0x40, #define MEMORY_DEVICE 0x0 CCLS = 0x41, @@ -83,6 +90,9 @@ enum { #define GET_POISON_LIST 0x0 #define INJECT_POISON 0x1 #define CLEAR_POISON 0x2 + #define GET_SCAN_MEDIA_CAPABILITIES 0x3 + #define SCAN_MEDIA 0x4 + #define GET_SCAN_MEDIA_RESULTS 0x5 DCD_CONFIG = 0x48, #define GET_DC_CONFIG 0x0 #define GET_DYN_CAP_EXT_LIST 0x1 @@ -235,7 +245,6 @@ static CXLRetCode cmd_events_get_records(const struct cxl_cmd *cmd, log_type = payload_in[0]; pl = (CXLGetEventPayload *)payload_out; - memset(pl, 0, sizeof(*pl)); max_recs = (cxlds->payload_size - CXL_EVENT_PAYLOAD_HDR_SIZE) / CXL_EVENT_RECORD_SIZE; @@ -273,7 +282,6 @@ static CXLRetCode cmd_events_get_interrupt_policy(const struct cxl_cmd *cmd, CXLEventLog *log; policy = (CXLEventInterruptPolicy *)payload_out; - memset(policy, 0, sizeof(*policy)); log = &cxlds->event_logs[CXL_EVENT_TYPE_INFO]; if (log->irq_enabled) { @@ -372,7 +380,6 @@ static CXLRetCode cmd_infostat_identify(const struct cxl_cmd *cmd, QEMU_BUILD_BUG_ON(sizeof(*is_identify) != 18); is_identify = (void *)payload_out; - memset(is_identify, 0, sizeof(*is_identify)); is_identify->pcie_vid = class->vendor_id; is_identify->pcie_did = class->device_id; if (object_dynamic_cast(OBJECT(cci->d), TYPE_CXL_USP)) { @@ -606,7 +613,6 @@ static CXLRetCode cmd_infostat_bg_op_sts(const struct cxl_cmd *cmd, QEMU_BUILD_BUG_ON(sizeof(*bg_op_status) != 8); bg_op_status = (void *)payload_out; - memset(bg_op_status, 0, sizeof(*bg_op_status)); bg_op_status->status = cci->bg.complete_pct << 1; if (cci->bg.runtime > 0) { bg_op_status->status |= 1U << 0; @@ -618,6 +624,9 @@ static CXLRetCode cmd_infostat_bg_op_sts(const struct cxl_cmd *cmd, return CXL_MBOX_SUCCESS; } +#define CXL_FW_SLOTS 2 +#define CXL_FW_SIZE 0x02000000 /* 32 mb */ + /* CXL r3.1 Section 8.2.9.3.1: Get FW Info (Opcode 0200h) */ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd, uint8_t *payload_in, @@ -647,17 +656,193 @@ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd, } fw_info = (void *)payload_out; - memset(fw_info, 0, sizeof(*fw_info)); - fw_info->slots_supported = 2; - fw_info->slot_info = BIT(0) | BIT(3); - fw_info->caps = 0; - pstrcpy(fw_info->fw_rev1, sizeof(fw_info->fw_rev1), "BWFW VERSION 0"); + fw_info->slots_supported = CXL_FW_SLOTS; + fw_info->slot_info = (cci->fw.active_slot & 0x7) | + ((cci->fw.staged_slot & 0x7) << 3); + fw_info->caps = BIT(0); /* online update supported */ + + if (cci->fw.slot[0]) { + pstrcpy(fw_info->fw_rev1, sizeof(fw_info->fw_rev1), "BWFW VERSION 0"); + } + if (cci->fw.slot[1]) { + pstrcpy(fw_info->fw_rev2, sizeof(fw_info->fw_rev2), "BWFW VERSION 1"); + } *len_out = sizeof(*fw_info); return CXL_MBOX_SUCCESS; } +/* CXL r3.1 section 8.2.9.3.2: Transfer FW (Opcode 0201h) */ +#define CXL_FW_XFER_ALIGNMENT 128 + +#define CXL_FW_XFER_ACTION_FULL 0x0 +#define CXL_FW_XFER_ACTION_INIT 0x1 +#define CXL_FW_XFER_ACTION_CONTINUE 0x2 +#define CXL_FW_XFER_ACTION_END 0x3 +#define CXL_FW_XFER_ACTION_ABORT 0x4 + +static CXLRetCode cmd_firmware_update_transfer(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + struct { + uint8_t action; + uint8_t slot; + uint8_t rsvd1[2]; + uint32_t offset; + uint8_t rsvd2[0x78]; + uint8_t data[]; + } QEMU_PACKED *fw_transfer = (void *)payload_in; + size_t offset, length; + + if (fw_transfer->action == CXL_FW_XFER_ACTION_ABORT) { + /* + * At this point there aren't any on-going transfers + * running in the bg - this is serialized before this + * call altogether. Just mark the state machine and + * disregard any other input. + */ + cci->fw.transferring = false; + return CXL_MBOX_SUCCESS; + } + + offset = fw_transfer->offset * CXL_FW_XFER_ALIGNMENT; + length = len - sizeof(*fw_transfer); + if (offset + length > CXL_FW_SIZE) { + return CXL_MBOX_INVALID_INPUT; + } + + if (cci->fw.transferring) { + if (fw_transfer->action == CXL_FW_XFER_ACTION_FULL || + fw_transfer->action == CXL_FW_XFER_ACTION_INIT) { + return CXL_MBOX_FW_XFER_IN_PROGRESS; + } + /* + * Abort partitioned package transfer if over 30 secs + * between parts. As opposed to the explicit ABORT action, + * semantically treat this condition as an error - as + * if a part action were passed without a previous INIT. + */ + if (difftime(time(NULL), cci->fw.last_partxfer) > 30.0) { + cci->fw.transferring = false; + return CXL_MBOX_INVALID_INPUT; + } + } else if (fw_transfer->action == CXL_FW_XFER_ACTION_CONTINUE || + fw_transfer->action == CXL_FW_XFER_ACTION_END) { + return CXL_MBOX_INVALID_INPUT; + } + + /* allow back-to-back retransmission */ + if ((offset != cci->fw.prev_offset || length != cci->fw.prev_len) && + (fw_transfer->action == CXL_FW_XFER_ACTION_CONTINUE || + fw_transfer->action == CXL_FW_XFER_ACTION_END)) { + /* verify no overlaps */ + if (offset < cci->fw.prev_offset + cci->fw.prev_len) { + return CXL_MBOX_FW_XFER_OUT_OF_ORDER; + } + } + + switch (fw_transfer->action) { + case CXL_FW_XFER_ACTION_FULL: /* ignores offset */ + case CXL_FW_XFER_ACTION_END: + if (fw_transfer->slot == 0 || + fw_transfer->slot == cci->fw.active_slot || + fw_transfer->slot > CXL_FW_SLOTS) { + return CXL_MBOX_FW_INVALID_SLOT; + } + + /* mark the slot used upon bg completion */ + break; + case CXL_FW_XFER_ACTION_INIT: + if (offset != 0) { + return CXL_MBOX_INVALID_INPUT; + } + + cci->fw.transferring = true; + cci->fw.prev_offset = offset; + cci->fw.prev_len = length; + break; + case CXL_FW_XFER_ACTION_CONTINUE: + cci->fw.prev_offset = offset; + cci->fw.prev_len = length; + break; + default: + return CXL_MBOX_INVALID_INPUT; + } + + if (fw_transfer->action == CXL_FW_XFER_ACTION_FULL) { + cci->bg.runtime = 10 * 1000UL; + } else { + cci->bg.runtime = 2 * 1000UL; + } + /* keep relevant context for bg completion */ + cci->fw.curr_action = fw_transfer->action; + cci->fw.curr_slot = fw_transfer->slot; + *len_out = 0; + + return CXL_MBOX_BG_STARTED; +} + +static void __do_firmware_xfer(CXLCCI *cci) +{ + switch (cci->fw.curr_action) { + case CXL_FW_XFER_ACTION_FULL: + case CXL_FW_XFER_ACTION_END: + cci->fw.slot[cci->fw.curr_slot - 1] = true; + cci->fw.transferring = false; + break; + case CXL_FW_XFER_ACTION_INIT: + case CXL_FW_XFER_ACTION_CONTINUE: + time(&cci->fw.last_partxfer); + break; + default: + break; + } +} + +/* CXL r3.1 section 8.2.9.3.3: Activate FW (Opcode 0202h) */ +static CXLRetCode cmd_firmware_update_activate(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + struct { + uint8_t action; + uint8_t slot; + } QEMU_PACKED *fw_activate = (void *)payload_in; + QEMU_BUILD_BUG_ON(sizeof(*fw_activate) != 0x2); + + if (fw_activate->slot == 0 || + fw_activate->slot == cci->fw.active_slot || + fw_activate->slot > CXL_FW_SLOTS) { + return CXL_MBOX_FW_INVALID_SLOT; + } + + /* ensure that an actual fw package is there */ + if (!cci->fw.slot[fw_activate->slot - 1]) { + return CXL_MBOX_FW_INVALID_SLOT; + } + + switch (fw_activate->action) { + case 0: /* online */ + cci->fw.active_slot = fw_activate->slot; + break; + case 1: /* reset */ + cci->fw.staged_slot = fw_activate->slot; + break; + default: + return CXL_MBOX_INVALID_INPUT; + } + + return CXL_MBOX_SUCCESS; +} + /* CXL r3.1 Section 8.2.9.4.1: Get Timestamp (Opcode 0300h) */ static CXLRetCode cmd_timestamp_get(const struct cxl_cmd *cmd, uint8_t *payload_in, @@ -768,6 +953,388 @@ static CXLRetCode cmd_logs_get_log(const struct cxl_cmd *cmd, return CXL_MBOX_SUCCESS; } +/* CXL r3.1 section 8.2.9.6: Features */ +/* + * Get Supported Features output payload + * CXL r3.1 section 8.2.9.6.1 Table 8-96 + */ +typedef struct CXLSupportedFeatureHeader { + uint16_t entries; + uint16_t nsuppfeats_dev; + uint32_t reserved; +} QEMU_PACKED CXLSupportedFeatureHeader; + +/* + * Get Supported Features Supported Feature Entry + * CXL r3.1 section 8.2.9.6.1 Table 8-97 + */ +typedef struct CXLSupportedFeatureEntry { + QemuUUID uuid; + uint16_t feat_index; + uint16_t get_feat_size; + uint16_t set_feat_size; + uint32_t attr_flags; + uint8_t get_feat_version; + uint8_t set_feat_version; + uint16_t set_feat_effects; + uint8_t rsvd[18]; +} QEMU_PACKED CXLSupportedFeatureEntry; + +/* + * Get Supported Features Supported Feature Entry + * CXL rev 3.1 section 8.2.9.6.1 Table 8-97 + */ +/* Supported Feature Entry : attribute flags */ +#define CXL_FEAT_ENTRY_ATTR_FLAG_CHANGABLE BIT(0) +#define CXL_FEAT_ENTRY_ATTR_FLAG_DEEPEST_RESET_PERSISTENCE_MASK GENMASK(3, 1) +#define CXL_FEAT_ENTRY_ATTR_FLAG_PERSIST_ACROSS_FIRMWARE_UPDATE BIT(4) +#define CXL_FEAT_ENTRY_ATTR_FLAG_SUPPORT_DEFAULT_SELECTION BIT(5) +#define CXL_FEAT_ENTRY_ATTR_FLAG_SUPPORT_SAVED_SELECTION BIT(6) + +/* Supported Feature Entry : set feature effects */ +#define CXL_FEAT_ENTRY_SFE_CONFIG_CHANGE_COLD_RESET BIT(0) +#define CXL_FEAT_ENTRY_SFE_IMMEDIATE_CONFIG_CHANGE BIT(1) +#define CXL_FEAT_ENTRY_SFE_IMMEDIATE_DATA_CHANGE BIT(2) +#define CXL_FEAT_ENTRY_SFE_IMMEDIATE_POLICY_CHANGE BIT(3) +#define CXL_FEAT_ENTRY_SFE_IMMEDIATE_LOG_CHANGE BIT(4) +#define CXL_FEAT_ENTRY_SFE_SECURITY_STATE_CHANGE BIT(5) +#define CXL_FEAT_ENTRY_SFE_BACKGROUND_OPERATION BIT(6) +#define CXL_FEAT_ENTRY_SFE_SUPPORT_SECONDARY_MAILBOX BIT(7) +#define CXL_FEAT_ENTRY_SFE_SUPPORT_ABORT_BACKGROUND_OPERATION BIT(8) +#define CXL_FEAT_ENTRY_SFE_CEL_VALID BIT(9) +#define CXL_FEAT_ENTRY_SFE_CONFIG_CHANGE_CONV_RESET BIT(10) +#define CXL_FEAT_ENTRY_SFE_CONFIG_CHANGE_CXL_RESET BIT(11) + +enum CXL_SUPPORTED_FEATURES_LIST { + CXL_FEATURE_PATROL_SCRUB = 0, + CXL_FEATURE_ECS, + CXL_FEATURE_MAX +}; + +/* Get Feature CXL 3.1 Spec 8.2.9.6.2 */ +/* + * Get Feature input payload + * CXL r3.1 section 8.2.9.6.2 Table 8-99 + */ +/* Get Feature : Payload in selection */ +enum CXL_GET_FEATURE_SELECTION { + CXL_GET_FEATURE_SEL_CURRENT_VALUE, + CXL_GET_FEATURE_SEL_DEFAULT_VALUE, + CXL_GET_FEATURE_SEL_SAVED_VALUE, + CXL_GET_FEATURE_SEL_MAX +}; + +/* Set Feature CXL 3.1 Spec 8.2.9.6.3 */ +/* + * Set Feature input payload + * CXL r3.1 section 8.2.9.6.3 Table 8-101 + */ +typedef struct CXLSetFeatureInHeader { + QemuUUID uuid; + uint32_t flags; + uint16_t offset; + uint8_t version; + uint8_t rsvd[9]; +} QEMU_PACKED QEMU_ALIGNED(16) CXLSetFeatureInHeader; + +/* Set Feature : Payload in flags */ +#define CXL_SET_FEATURE_FLAG_DATA_TRANSFER_MASK 0x7 +enum CXL_SET_FEATURE_FLAG_DATA_TRANSFER { + CXL_SET_FEATURE_FLAG_FULL_DATA_TRANSFER, + CXL_SET_FEATURE_FLAG_INITIATE_DATA_TRANSFER, + CXL_SET_FEATURE_FLAG_CONTINUE_DATA_TRANSFER, + CXL_SET_FEATURE_FLAG_FINISH_DATA_TRANSFER, + CXL_SET_FEATURE_FLAG_ABORT_DATA_TRANSFER, + CXL_SET_FEATURE_FLAG_DATA_TRANSFER_MAX +}; +#define CXL_SET_FEAT_DATA_SAVED_ACROSS_RESET BIT(3) + +/* CXL r3.1 section 8.2.9.9.11.1: Device Patrol Scrub Control Feature */ +static const QemuUUID patrol_scrub_uuid = { + .data = UUID(0x96dad7d6, 0xfde8, 0x482b, 0xa7, 0x33, + 0x75, 0x77, 0x4e, 0x06, 0xdb, 0x8a) +}; + +typedef struct CXLMemPatrolScrubSetFeature { + CXLSetFeatureInHeader hdr; + CXLMemPatrolScrubWriteAttrs feat_data; +} QEMU_PACKED QEMU_ALIGNED(16) CXLMemPatrolScrubSetFeature; + +/* + * CXL r3.1 section 8.2.9.9.11.2: + * DDR5 Error Check Scrub (ECS) Control Feature + */ +static const QemuUUID ecs_uuid = { + .data = UUID(0xe5b13f22, 0x2328, 0x4a14, 0xb8, 0xba, + 0xb9, 0x69, 0x1e, 0x89, 0x33, 0x86) +}; + +typedef struct CXLMemECSSetFeature { + CXLSetFeatureInHeader hdr; + CXLMemECSWriteAttrs feat_data[]; +} QEMU_PACKED QEMU_ALIGNED(16) CXLMemECSSetFeature; + +/* CXL r3.1 section 8.2.9.6.1: Get Supported Features (Opcode 0500h) */ +static CXLRetCode cmd_features_get_supported(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len_in, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + struct { + uint32_t count; + uint16_t start_index; + uint16_t reserved; + } QEMU_PACKED QEMU_ALIGNED(16) * get_feats_in = (void *)payload_in; + + struct { + CXLSupportedFeatureHeader hdr; + CXLSupportedFeatureEntry feat_entries[]; + } QEMU_PACKED QEMU_ALIGNED(16) * get_feats_out = (void *)payload_out; + uint16_t index, req_entries; + uint16_t entry; + + if (!object_dynamic_cast(OBJECT(cci->d), TYPE_CXL_TYPE3)) { + return CXL_MBOX_UNSUPPORTED; + } + if (get_feats_in->count < sizeof(CXLSupportedFeatureHeader) || + get_feats_in->start_index >= CXL_FEATURE_MAX) { + return CXL_MBOX_INVALID_INPUT; + } + + req_entries = (get_feats_in->count - + sizeof(CXLSupportedFeatureHeader)) / + sizeof(CXLSupportedFeatureEntry); + req_entries = MIN(req_entries, + (CXL_FEATURE_MAX - get_feats_in->start_index)); + + for (entry = 0, index = get_feats_in->start_index; + entry < req_entries; index++) { + switch (index) { + case CXL_FEATURE_PATROL_SCRUB: + /* Fill supported feature entry for device patrol scrub control */ + get_feats_out->feat_entries[entry++] = + (struct CXLSupportedFeatureEntry) { + .uuid = patrol_scrub_uuid, + .feat_index = index, + .get_feat_size = sizeof(CXLMemPatrolScrubReadAttrs), + .set_feat_size = sizeof(CXLMemPatrolScrubWriteAttrs), + .attr_flags = CXL_FEAT_ENTRY_ATTR_FLAG_CHANGABLE, + .get_feat_version = CXL_MEMDEV_PS_GET_FEATURE_VERSION, + .set_feat_version = CXL_MEMDEV_PS_SET_FEATURE_VERSION, + .set_feat_effects = CXL_FEAT_ENTRY_SFE_IMMEDIATE_CONFIG_CHANGE | + CXL_FEAT_ENTRY_SFE_CEL_VALID, + }; + break; + case CXL_FEATURE_ECS: + /* Fill supported feature entry for device DDR5 ECS control */ + get_feats_out->feat_entries[entry++] = + (struct CXLSupportedFeatureEntry) { + .uuid = ecs_uuid, + .feat_index = index, + .get_feat_size = CXL_ECS_NUM_MEDIA_FRUS * + sizeof(CXLMemECSReadAttrs), + .set_feat_size = CXL_ECS_NUM_MEDIA_FRUS * + sizeof(CXLMemECSWriteAttrs), + .attr_flags = CXL_FEAT_ENTRY_ATTR_FLAG_CHANGABLE, + .get_feat_version = CXL_ECS_GET_FEATURE_VERSION, + .set_feat_version = CXL_ECS_SET_FEATURE_VERSION, + .set_feat_effects = CXL_FEAT_ENTRY_SFE_IMMEDIATE_CONFIG_CHANGE | + CXL_FEAT_ENTRY_SFE_CEL_VALID, + }; + break; + default: + __builtin_unreachable(); + } + } + get_feats_out->hdr.nsuppfeats_dev = CXL_FEATURE_MAX; + get_feats_out->hdr.entries = req_entries; + *len_out = sizeof(CXLSupportedFeatureHeader) + + req_entries * sizeof(CXLSupportedFeatureEntry); + + return CXL_MBOX_SUCCESS; +} + +/* CXL r3.1 section 8.2.9.6.2: Get Feature (Opcode 0501h) */ +static CXLRetCode cmd_features_get_feature(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len_in, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + struct { + QemuUUID uuid; + uint16_t offset; + uint16_t count; + uint8_t selection; + } QEMU_PACKED QEMU_ALIGNED(16) * get_feature; + uint16_t bytes_to_copy = 0; + CXLType3Dev *ct3d; + CXLSetFeatureInfo *set_feat_info; + + if (!object_dynamic_cast(OBJECT(cci->d), TYPE_CXL_TYPE3)) { + return CXL_MBOX_UNSUPPORTED; + } + + ct3d = CXL_TYPE3(cci->d); + get_feature = (void *)payload_in; + + set_feat_info = &ct3d->set_feat_info; + if (qemu_uuid_is_equal(&get_feature->uuid, &set_feat_info->uuid)) { + return CXL_MBOX_FEATURE_TRANSFER_IN_PROGRESS; + } + + if (get_feature->selection != CXL_GET_FEATURE_SEL_CURRENT_VALUE) { + return CXL_MBOX_UNSUPPORTED; + } + if (get_feature->offset + get_feature->count > cci->payload_max) { + return CXL_MBOX_INVALID_INPUT; + } + + if (qemu_uuid_is_equal(&get_feature->uuid, &patrol_scrub_uuid)) { + if (get_feature->offset >= sizeof(CXLMemPatrolScrubReadAttrs)) { + return CXL_MBOX_INVALID_INPUT; + } + bytes_to_copy = sizeof(CXLMemPatrolScrubReadAttrs) - + get_feature->offset; + bytes_to_copy = MIN(bytes_to_copy, get_feature->count); + memcpy(payload_out, + (uint8_t *)&ct3d->patrol_scrub_attrs + get_feature->offset, + bytes_to_copy); + } else if (qemu_uuid_is_equal(&get_feature->uuid, &ecs_uuid)) { + if (get_feature->offset >= CXL_ECS_NUM_MEDIA_FRUS * + sizeof(CXLMemECSReadAttrs)) { + return CXL_MBOX_INVALID_INPUT; + } + bytes_to_copy = CXL_ECS_NUM_MEDIA_FRUS * + sizeof(CXLMemECSReadAttrs) - + get_feature->offset; + bytes_to_copy = MIN(bytes_to_copy, get_feature->count); + memcpy(payload_out, + (uint8_t *)&ct3d->ecs_attrs + get_feature->offset, + bytes_to_copy); + } else { + return CXL_MBOX_UNSUPPORTED; + } + + *len_out = bytes_to_copy; + + return CXL_MBOX_SUCCESS; +} + +/* CXL r3.1 section 8.2.9.6.3: Set Feature (Opcode 0502h) */ +static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len_in, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + CXLSetFeatureInHeader *hdr = (void *)payload_in; + CXLMemPatrolScrubWriteAttrs *ps_write_attrs; + CXLMemPatrolScrubSetFeature *ps_set_feature; + CXLMemECSWriteAttrs *ecs_write_attrs; + CXLMemECSSetFeature *ecs_set_feature; + CXLSetFeatureInfo *set_feat_info; + uint16_t bytes_to_copy = 0; + uint8_t data_transfer_flag; + CXLType3Dev *ct3d; + uint16_t count; + + + if (!object_dynamic_cast(OBJECT(cci->d), TYPE_CXL_TYPE3)) { + return CXL_MBOX_UNSUPPORTED; + } + ct3d = CXL_TYPE3(cci->d); + set_feat_info = &ct3d->set_feat_info; + + if (!qemu_uuid_is_null(&set_feat_info->uuid) && + !qemu_uuid_is_equal(&hdr->uuid, &set_feat_info->uuid)) { + return CXL_MBOX_FEATURE_TRANSFER_IN_PROGRESS; + } + if (hdr->flags & CXL_SET_FEAT_DATA_SAVED_ACROSS_RESET) { + set_feat_info->data_saved_across_reset = true; + } else { + set_feat_info->data_saved_across_reset = false; + } + + data_transfer_flag = + hdr->flags & CXL_SET_FEATURE_FLAG_DATA_TRANSFER_MASK; + if (data_transfer_flag == CXL_SET_FEATURE_FLAG_INITIATE_DATA_TRANSFER) { + set_feat_info->uuid = hdr->uuid; + set_feat_info->data_size = 0; + } + set_feat_info->data_transfer_flag = data_transfer_flag; + set_feat_info->data_offset = hdr->offset; + bytes_to_copy = len_in - sizeof(CXLSetFeatureInHeader); + + if (qemu_uuid_is_equal(&hdr->uuid, &patrol_scrub_uuid)) { + if (hdr->version != CXL_MEMDEV_PS_SET_FEATURE_VERSION) { + return CXL_MBOX_UNSUPPORTED; + } + + ps_set_feature = (void *)payload_in; + ps_write_attrs = &ps_set_feature->feat_data; + memcpy((uint8_t *)&ct3d->patrol_scrub_wr_attrs + hdr->offset, + ps_write_attrs, + bytes_to_copy); + set_feat_info->data_size += bytes_to_copy; + + if (data_transfer_flag == CXL_SET_FEATURE_FLAG_FULL_DATA_TRANSFER || + data_transfer_flag == CXL_SET_FEATURE_FLAG_FINISH_DATA_TRANSFER) { + ct3d->patrol_scrub_attrs.scrub_cycle &= ~0xFF; + ct3d->patrol_scrub_attrs.scrub_cycle |= + ct3d->patrol_scrub_wr_attrs.scrub_cycle_hr & 0xFF; + ct3d->patrol_scrub_attrs.scrub_flags &= ~0x1; + ct3d->patrol_scrub_attrs.scrub_flags |= + ct3d->patrol_scrub_wr_attrs.scrub_flags & 0x1; + } + } else if (qemu_uuid_is_equal(&hdr->uuid, + &ecs_uuid)) { + if (hdr->version != CXL_ECS_SET_FEATURE_VERSION) { + return CXL_MBOX_UNSUPPORTED; + } + + ecs_set_feature = (void *)payload_in; + ecs_write_attrs = ecs_set_feature->feat_data; + memcpy((uint8_t *)ct3d->ecs_wr_attrs + hdr->offset, + ecs_write_attrs, + bytes_to_copy); + set_feat_info->data_size += bytes_to_copy; + + if (data_transfer_flag == CXL_SET_FEATURE_FLAG_FULL_DATA_TRANSFER || + data_transfer_flag == CXL_SET_FEATURE_FLAG_FINISH_DATA_TRANSFER) { + for (count = 0; count < CXL_ECS_NUM_MEDIA_FRUS; count++) { + ct3d->ecs_attrs[count].ecs_log_cap = + ct3d->ecs_wr_attrs[count].ecs_log_cap; + ct3d->ecs_attrs[count].ecs_config = + ct3d->ecs_wr_attrs[count].ecs_config & 0x1F; + } + } + } else { + return CXL_MBOX_UNSUPPORTED; + } + + if (data_transfer_flag == CXL_SET_FEATURE_FLAG_FULL_DATA_TRANSFER || + data_transfer_flag == CXL_SET_FEATURE_FLAG_FINISH_DATA_TRANSFER || + data_transfer_flag == CXL_SET_FEATURE_FLAG_ABORT_DATA_TRANSFER) { + memset(&set_feat_info->uuid, 0, sizeof(QemuUUID)); + if (qemu_uuid_is_equal(&hdr->uuid, &patrol_scrub_uuid)) { + memset(&ct3d->patrol_scrub_wr_attrs, 0, set_feat_info->data_size); + } else if (qemu_uuid_is_equal(&hdr->uuid, &ecs_uuid)) { + memset(ct3d->ecs_wr_attrs, 0, set_feat_info->data_size); + } + set_feat_info->data_transfer_flag = 0; + set_feat_info->data_saved_across_reset = false; + set_feat_info->data_offset = 0; + set_feat_info->data_size = 0; + } + + return CXL_MBOX_SUCCESS; +} + /* CXL r3.1 Section 8.2.9.9.1.1: Identify Memory Device (Opcode 4000h) */ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd, uint8_t *payload_in, @@ -805,7 +1372,6 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd, } id = (void *)payload_out; - memset(id, 0, sizeof(*id)); snprintf(id->fw_revision, 0x10, "BWFW VERSION %02d", 0); @@ -953,6 +1519,7 @@ static void __do_sanitization(CXLType3Dev *ct3d) memset(lsa, 0, memory_region_size(mr)); } } + cxl_discard_all_event_records(&ct3d->cxl_dstate); } /* @@ -1095,7 +1662,6 @@ static CXLRetCode cmd_media_get_poison_list(const struct cxl_cmd *cmd, out_pl_len = sizeof(*out) + record_count * sizeof(out->records[0]); assert(out_pl_len <= CXL_MAILBOX_MAX_PAYLOAD_SIZE); - memset(out, 0, out_pl_len); QLIST_FOREACH(ent, poison_list, node) { uint64_t start, stop; @@ -1117,6 +1683,10 @@ static CXLRetCode cmd_media_get_poison_list(const struct cxl_cmd *cmd, out->flags = (1 << 1); stq_le_p(&out->overflow_timestamp, ct3d->poison_list_overflow_ts); } + if (scan_media_running(cci)) { + out->flags |= (1 << 2); + } + stw_le_p(&out->count, record_count); *len_out = out_pl_len; return CXL_MBOX_SUCCESS; @@ -1146,6 +1716,16 @@ static CXLRetCode cmd_media_inject_poison(const struct cxl_cmd *cmd, return CXL_MBOX_SUCCESS; } } + /* + * Freeze the list if there is an on-going scan media operation. + */ + if (scan_media_running(cci)) { + /* + * XXX: Spec is ambiguous - is this case considered + * a successful return despite not adding to the list? + */ + goto success; + } if (ct3d->poison_list_cnt == CXL_POISON_LIST_LIMIT) { return CXL_MBOX_INJECT_POISON_LIMIT; @@ -1161,6 +1741,7 @@ static CXLRetCode cmd_media_inject_poison(const struct cxl_cmd *cmd, */ QLIST_INSERT_HEAD(poison_list, p, node); ct3d->poison_list_cnt++; +success: *len_out = 0; return CXL_MBOX_SUCCESS; @@ -1200,6 +1781,17 @@ static CXLRetCode cmd_media_clear_poison(const struct cxl_cmd *cmd, } } + /* + * Freeze the list if there is an on-going scan media operation. + */ + if (scan_media_running(cci)) { + /* + * XXX: Spec is ambiguous - is this case considered + * a successful return despite not removing from the list? + */ + goto success; + } + QLIST_FOREACH(ent, poison_list, node) { /* * Test for contained in entry. Simpler than general case @@ -1210,7 +1802,7 @@ static CXLRetCode cmd_media_clear_poison(const struct cxl_cmd *cmd, } } if (!ent) { - return CXL_MBOX_SUCCESS; + goto success; } QLIST_REMOVE(ent, node); @@ -1247,12 +1839,262 @@ static CXLRetCode cmd_media_clear_poison(const struct cxl_cmd *cmd, } /* Any fragments have been added, free original entry */ g_free(ent); +success: *len_out = 0; return CXL_MBOX_SUCCESS; } /* + * CXL r3.1 section 8.2.9.9.4.4: Get Scan Media Capabilities + */ +static CXLRetCode +cmd_media_get_scan_media_capabilities(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len_in, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + struct get_scan_media_capabilities_pl { + uint64_t pa; + uint64_t length; + } QEMU_PACKED; + + struct get_scan_media_capabilities_out_pl { + uint32_t estimated_runtime_ms; + }; + + CXLType3Dev *ct3d = CXL_TYPE3(cci->d); + CXLDeviceState *cxl_dstate = &ct3d->cxl_dstate; + struct get_scan_media_capabilities_pl *in = (void *)payload_in; + struct get_scan_media_capabilities_out_pl *out = (void *)payload_out; + uint64_t query_start; + uint64_t query_length; + + query_start = ldq_le_p(&in->pa); + /* 64 byte alignment required */ + if (query_start & 0x3f) { + return CXL_MBOX_INVALID_INPUT; + } + query_length = ldq_le_p(&in->length) * CXL_CACHE_LINE_SIZE; + + if (query_start + query_length > cxl_dstate->static_mem_size) { + return CXL_MBOX_INVALID_PA; + } + + /* + * Just use 400 nanosecond access/read latency + 100 ns for + * the cost of updating the poison list. For small enough + * chunks return at least 1 ms. + */ + stl_le_p(&out->estimated_runtime_ms, + MAX(1, query_length * (0.0005L / 64))); + + *len_out = sizeof(*out); + return CXL_MBOX_SUCCESS; +} + +static void __do_scan_media(CXLType3Dev *ct3d) +{ + CXLPoison *ent; + unsigned int results_cnt = 0; + + QLIST_FOREACH(ent, &ct3d->scan_media_results, node) { + results_cnt++; + } + + /* only scan media may clear the overflow */ + if (ct3d->poison_list_overflowed && + ct3d->poison_list_cnt == results_cnt) { + cxl_clear_poison_list_overflowed(ct3d); + } + /* scan media has run since last conventional reset */ + ct3d->scan_media_hasrun = true; +} + +/* + * CXL r3.1 section 8.2.9.9.4.5: Scan Media + */ +static CXLRetCode cmd_media_scan_media(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len_in, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + struct scan_media_pl { + uint64_t pa; + uint64_t length; + uint8_t flags; + } QEMU_PACKED; + + struct scan_media_pl *in = (void *)payload_in; + CXLType3Dev *ct3d = CXL_TYPE3(cci->d); + CXLDeviceState *cxl_dstate = &ct3d->cxl_dstate; + uint64_t query_start; + uint64_t query_length; + CXLPoison *ent, *next; + + query_start = ldq_le_p(&in->pa); + /* 64 byte alignment required */ + if (query_start & 0x3f) { + return CXL_MBOX_INVALID_INPUT; + } + query_length = ldq_le_p(&in->length) * CXL_CACHE_LINE_SIZE; + + if (query_start + query_length > cxl_dstate->static_mem_size) { + return CXL_MBOX_INVALID_PA; + } + if (ct3d->dc.num_regions && query_start + query_length >= + cxl_dstate->static_mem_size + ct3d->dc.total_capacity) { + return CXL_MBOX_INVALID_PA; + } + + if (in->flags == 0) { /* TODO */ + qemu_log_mask(LOG_UNIMP, + "Scan Media Event Log is unsupported\n"); + } + + /* any previous results are discarded upon a new Scan Media */ + QLIST_FOREACH_SAFE(ent, &ct3d->scan_media_results, node, next) { + QLIST_REMOVE(ent, node); + g_free(ent); + } + + /* kill the poison list - it will be recreated */ + if (ct3d->poison_list_overflowed) { + QLIST_FOREACH_SAFE(ent, &ct3d->poison_list, node, next) { + QLIST_REMOVE(ent, node); + g_free(ent); + ct3d->poison_list_cnt--; + } + } + + /* + * Scan the backup list and move corresponding entries + * into the results list, updating the poison list + * when possible. + */ + QLIST_FOREACH_SAFE(ent, &ct3d->poison_list_bkp, node, next) { + CXLPoison *res; + + if (ent->start >= query_start + query_length || + ent->start + ent->length <= query_start) { + continue; + } + + /* + * If a Get Poison List cmd comes in while this + * scan is being done, it will see the new complete + * list, while setting the respective flag. + */ + if (ct3d->poison_list_cnt < CXL_POISON_LIST_LIMIT) { + CXLPoison *p = g_new0(CXLPoison, 1); + + p->start = ent->start; + p->length = ent->length; + p->type = ent->type; + QLIST_INSERT_HEAD(&ct3d->poison_list, p, node); + ct3d->poison_list_cnt++; + } + + res = g_new0(CXLPoison, 1); + res->start = ent->start; + res->length = ent->length; + res->type = ent->type; + QLIST_INSERT_HEAD(&ct3d->scan_media_results, res, node); + + QLIST_REMOVE(ent, node); + g_free(ent); + } + + cci->bg.runtime = MAX(1, query_length * (0.0005L / 64)); + *len_out = 0; + + return CXL_MBOX_BG_STARTED; +} + +/* + * CXL r3.1 section 8.2.9.9.4.6: Get Scan Media Results + */ +static CXLRetCode cmd_media_get_scan_media_results(const struct cxl_cmd *cmd, + uint8_t *payload_in, + size_t len_in, + uint8_t *payload_out, + size_t *len_out, + CXLCCI *cci) +{ + struct get_scan_media_results_out_pl { + uint64_t dpa_restart; + uint64_t length; + uint8_t flags; + uint8_t rsvd1; + uint16_t count; + uint8_t rsvd2[0xc]; + struct { + uint64_t addr; + uint32_t length; + uint32_t resv; + } QEMU_PACKED records[]; + } QEMU_PACKED; + + struct get_scan_media_results_out_pl *out = (void *)payload_out; + CXLType3Dev *ct3d = CXL_TYPE3(cci->d); + CXLPoisonList *scan_media_results = &ct3d->scan_media_results; + CXLPoison *ent, *next; + uint16_t total_count = 0, record_count = 0, i = 0; + uint16_t out_pl_len; + + if (!ct3d->scan_media_hasrun) { + return CXL_MBOX_UNSUPPORTED; + } + + /* + * Calculate limits, all entries are within the same address range of the + * last scan media call. + */ + QLIST_FOREACH(ent, scan_media_results, node) { + size_t rec_size = record_count * sizeof(out->records[0]); + + if (sizeof(*out) + rec_size < CXL_MAILBOX_MAX_PAYLOAD_SIZE) { + record_count++; + } + total_count++; + } + + out_pl_len = sizeof(*out) + record_count * sizeof(out->records[0]); + assert(out_pl_len <= CXL_MAILBOX_MAX_PAYLOAD_SIZE); + + memset(out, 0, out_pl_len); + QLIST_FOREACH_SAFE(ent, scan_media_results, node, next) { + uint64_t start, stop; + + if (i == record_count) { + break; + } + + start = ROUND_DOWN(ent->start, 64ull); + stop = ROUND_DOWN(ent->start, 64ull) + ent->length; + stq_le_p(&out->records[i].addr, start | (ent->type & 0x7)); + stl_le_p(&out->records[i].length, (stop - start) / CXL_CACHE_LINE_SIZE); + i++; + + /* consume the returning entry */ + QLIST_REMOVE(ent, node); + g_free(ent); + } + + stw_le_p(&out->count, record_count); + if (total_count > record_count) { + out->flags = (1 << 0); /* More Media Error Records */ + } + + *len_out = out_pl_len; + return CXL_MBOX_SUCCESS; +} + +/* * CXL r3.1 section 8.2.9.9.9.1: Get Dynamic Capacity Configuration * (Opcode: 4800h) */ @@ -1822,40 +2664,51 @@ static CXLRetCode cmd_dcd_release_dyn_cap(const struct cxl_cmd *cmd, return CXL_MBOX_SUCCESS; } -#define IMMEDIATE_CONFIG_CHANGE (1 << 1) -#define IMMEDIATE_DATA_CHANGE (1 << 2) -#define IMMEDIATE_POLICY_CHANGE (1 << 3) -#define IMMEDIATE_LOG_CHANGE (1 << 4) -#define SECURITY_STATE_CHANGE (1 << 5) -#define BACKGROUND_OPERATION (1 << 6) - static const struct cxl_cmd cxl_cmd_set[256][256] = { [EVENTS][GET_RECORDS] = { "EVENTS_GET_RECORDS", cmd_events_get_records, 1, 0 }, [EVENTS][CLEAR_RECORDS] = { "EVENTS_CLEAR_RECORDS", - cmd_events_clear_records, ~0, IMMEDIATE_LOG_CHANGE }, + cmd_events_clear_records, ~0, CXL_MBOX_IMMEDIATE_LOG_CHANGE }, [EVENTS][GET_INTERRUPT_POLICY] = { "EVENTS_GET_INTERRUPT_POLICY", cmd_events_get_interrupt_policy, 0, 0 }, [EVENTS][SET_INTERRUPT_POLICY] = { "EVENTS_SET_INTERRUPT_POLICY", cmd_events_set_interrupt_policy, - ~0, IMMEDIATE_CONFIG_CHANGE }, + ~0, CXL_MBOX_IMMEDIATE_CONFIG_CHANGE }, [FIRMWARE_UPDATE][GET_INFO] = { "FIRMWARE_UPDATE_GET_INFO", cmd_firmware_update_get_info, 0, 0 }, + [FIRMWARE_UPDATE][TRANSFER] = { "FIRMWARE_UPDATE_TRANSFER", + cmd_firmware_update_transfer, ~0, CXL_MBOX_BACKGROUND_OPERATION }, + [FIRMWARE_UPDATE][ACTIVATE] = { "FIRMWARE_UPDATE_ACTIVATE", + cmd_firmware_update_activate, 2, CXL_MBOX_BACKGROUND_OPERATION }, [TIMESTAMP][GET] = { "TIMESTAMP_GET", cmd_timestamp_get, 0, 0 }, [TIMESTAMP][SET] = { "TIMESTAMP_SET", cmd_timestamp_set, - 8, IMMEDIATE_POLICY_CHANGE }, + 8, CXL_MBOX_IMMEDIATE_POLICY_CHANGE }, [LOGS][GET_SUPPORTED] = { "LOGS_GET_SUPPORTED", cmd_logs_get_supported, 0, 0 }, [LOGS][GET_LOG] = { "LOGS_GET_LOG", cmd_logs_get_log, 0x18, 0 }, + [FEATURES][GET_SUPPORTED] = { "FEATURES_GET_SUPPORTED", + cmd_features_get_supported, 0x8, 0 }, + [FEATURES][GET_FEATURE] = { "FEATURES_GET_FEATURE", + cmd_features_get_feature, 0x15, 0 }, + [FEATURES][SET_FEATURE] = { "FEATURES_SET_FEATURE", + cmd_features_set_feature, + ~0, + (CXL_MBOX_IMMEDIATE_CONFIG_CHANGE | + CXL_MBOX_IMMEDIATE_DATA_CHANGE | + CXL_MBOX_IMMEDIATE_POLICY_CHANGE | + CXL_MBOX_IMMEDIATE_LOG_CHANGE | + CXL_MBOX_SECURITY_STATE_CHANGE)}, [IDENTIFY][MEMORY_DEVICE] = { "IDENTIFY_MEMORY_DEVICE", cmd_identify_memory_device, 0, 0 }, [CCLS][GET_PARTITION_INFO] = { "CCLS_GET_PARTITION_INFO", cmd_ccls_get_partition_info, 0, 0 }, [CCLS][GET_LSA] = { "CCLS_GET_LSA", cmd_ccls_get_lsa, 8, 0 }, [CCLS][SET_LSA] = { "CCLS_SET_LSA", cmd_ccls_set_lsa, - ~0, IMMEDIATE_CONFIG_CHANGE | IMMEDIATE_DATA_CHANGE }, + ~0, CXL_MBOX_IMMEDIATE_CONFIG_CHANGE | CXL_MBOX_IMMEDIATE_DATA_CHANGE }, [SANITIZE][OVERWRITE] = { "SANITIZE_OVERWRITE", cmd_sanitize_overwrite, 0, - IMMEDIATE_DATA_CHANGE | SECURITY_STATE_CHANGE | BACKGROUND_OPERATION }, + (CXL_MBOX_IMMEDIATE_DATA_CHANGE | + CXL_MBOX_SECURITY_STATE_CHANGE | + CXL_MBOX_BACKGROUND_OPERATION)}, [PERSISTENT_MEM][GET_SECURITY_STATE] = { "GET_SECURITY_STATE", cmd_get_security_state, 0, 0 }, [MEDIA_AND_POISON][GET_POISON_LIST] = { "MEDIA_AND_POISON_GET_POISON_LIST", @@ -1864,6 +2717,14 @@ static const struct cxl_cmd cxl_cmd_set[256][256] = { cmd_media_inject_poison, 8, 0 }, [MEDIA_AND_POISON][CLEAR_POISON] = { "MEDIA_AND_POISON_CLEAR_POISON", cmd_media_clear_poison, 72, 0 }, + [MEDIA_AND_POISON][GET_SCAN_MEDIA_CAPABILITIES] = { + "MEDIA_AND_POISON_GET_SCAN_MEDIA_CAPABILITIES", + cmd_media_get_scan_media_capabilities, 16, 0 }, + [MEDIA_AND_POISON][SCAN_MEDIA] = { "MEDIA_AND_POISON_SCAN_MEDIA", + cmd_media_scan_media, 17, CXL_MBOX_BACKGROUND_OPERATION }, + [MEDIA_AND_POISON][GET_SCAN_MEDIA_RESULTS] = { + "MEDIA_AND_POISON_GET_SCAN_MEDIA_RESULTS", + cmd_media_get_scan_media_results, 0, 0 }, }; static const struct cxl_cmd cxl_cmd_set_dcd[256][256] = { @@ -1874,10 +2735,10 @@ static const struct cxl_cmd cxl_cmd_set_dcd[256][256] = { 8, 0 }, [DCD_CONFIG][ADD_DYN_CAP_RSP] = { "DCD_ADD_DYNAMIC_CAPACITY_RESPONSE", cmd_dcd_add_dyn_cap_rsp, - ~0, IMMEDIATE_DATA_CHANGE }, + ~0, CXL_MBOX_IMMEDIATE_DATA_CHANGE }, [DCD_CONFIG][RELEASE_DYN_CAP] = { "DCD_RELEASE_DYNAMIC_CAPACITY", cmd_dcd_release_dyn_cap, - ~0, IMMEDIATE_DATA_CHANGE }, + ~0, CXL_MBOX_IMMEDIATE_DATA_CHANGE }, }; static const struct cxl_cmd cxl_cmd_set_sw[256][256] = { @@ -1885,8 +2746,8 @@ static const struct cxl_cmd cxl_cmd_set_sw[256][256] = { [INFOSTAT][BACKGROUND_OPERATION_STATUS] = { "BACKGROUND_OPERATION_STATUS", cmd_infostat_bg_op_sts, 0, 0 }, [TIMESTAMP][GET] = { "TIMESTAMP_GET", cmd_timestamp_get, 0, 0 }, - [TIMESTAMP][SET] = { "TIMESTAMP_SET", cmd_timestamp_set, 0, - IMMEDIATE_POLICY_CHANGE }, + [TIMESTAMP][SET] = { "TIMESTAMP_SET", cmd_timestamp_set, 8, + CXL_MBOX_IMMEDIATE_POLICY_CHANGE }, [LOGS][GET_SUPPORTED] = { "LOGS_GET_SUPPORTED", cmd_logs_get_supported, 0, 0 }, [LOGS][GET_LOG] = { "LOGS_GET_LOG", cmd_logs_get_log, 0x18, 0 }, @@ -1913,6 +2774,7 @@ int cxl_process_cci_message(CXLCCI *cci, uint8_t set, uint8_t cmd, int ret; const struct cxl_cmd *cxl_cmd; opcode_handler h; + CXLDeviceState *cxl_dstate; *len_out = 0; cxl_cmd = &cci->cxl_cmd_set[set][cmd]; @@ -1928,28 +2790,34 @@ int cxl_process_cci_message(CXLCCI *cci, uint8_t set, uint8_t cmd, } /* Only one bg command at a time */ - if ((cxl_cmd->effect & BACKGROUND_OPERATION) && + if ((cxl_cmd->effect & CXL_MBOX_BACKGROUND_OPERATION) && cci->bg.runtime > 0) { return CXL_MBOX_BUSY; } - /* forbid any selected commands while overwriting */ - if (sanitize_running(cci)) { - if (h == cmd_events_get_records || - h == cmd_ccls_get_partition_info || - h == cmd_ccls_set_lsa || - h == cmd_ccls_get_lsa || - h == cmd_logs_get_log || - h == cmd_media_get_poison_list || - h == cmd_media_inject_poison || - h == cmd_media_clear_poison || - h == cmd_sanitize_overwrite) { - return CXL_MBOX_MEDIA_DISABLED; + /* forbid any selected commands while the media is disabled */ + if (object_dynamic_cast(OBJECT(cci->d), TYPE_CXL_TYPE3)) { + cxl_dstate = &CXL_TYPE3(cci->d)->cxl_dstate; + + if (cxl_dev_media_disabled(cxl_dstate)) { + if (h == cmd_events_get_records || + h == cmd_ccls_get_partition_info || + h == cmd_ccls_set_lsa || + h == cmd_ccls_get_lsa || + h == cmd_logs_get_log || + h == cmd_media_get_poison_list || + h == cmd_media_inject_poison || + h == cmd_media_clear_poison || + h == cmd_sanitize_overwrite || + h == cmd_firmware_update_transfer || + h == cmd_firmware_update_activate) { + return CXL_MBOX_MEDIA_DISABLED; + } } } ret = (*h)(cxl_cmd, pl_in, len_in, pl_out, len_out, cci); - if ((cxl_cmd->effect & BACKGROUND_OPERATION) && + if ((cxl_cmd->effect & CXL_MBOX_BACKGROUND_OPERATION) && ret == CXL_MBOX_BG_STARTED) { *bg_started = true; } else { @@ -1987,6 +2855,9 @@ static void bg_timercb(void *opaque) cci->bg.complete_pct = 100; cci->bg.ret_code = ret; switch (cci->bg.opcode) { + case 0x0201: /* fw transfer */ + __do_firmware_xfer(cci); + break; case 0x4400: /* sanitize */ { CXLType3Dev *ct3d = CXL_TYPE3(cci->d); @@ -1995,8 +2866,13 @@ static void bg_timercb(void *opaque) cxl_dev_enable_media(&ct3d->cxl_dstate); } break; - case 0x4304: /* TODO: scan media */ + case 0x4304: /* scan media */ + { + CXLType3Dev *ct3d = CXL_TYPE3(cci->d); + + __do_scan_media(ct3d); break; + } default: __builtin_unreachable(); break; @@ -2053,6 +2929,10 @@ void cxl_init_cci(CXLCCI *cci, size_t payload_max) cci->bg.runtime = 0; cci->bg.timer = timer_new_ms(QEMU_CLOCK_VIRTUAL, bg_timercb, cci); + + memset(&cci->fw, 0, sizeof(cci->fw)); + cci->fw.active_slot = 1; + cci->fw.slot[cci->fw.active_slot - 1] = true; } static void cxl_copy_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmds)[256]) diff --git a/hw/display/virtio-gpu-gl.c b/hw/display/virtio-gpu-gl.c index e06be60dfb..952820a425 100644 --- a/hw/display/virtio-gpu-gl.c +++ b/hw/display/virtio-gpu-gl.c @@ -170,3 +170,4 @@ static void virtio_register_types(void) type_init(virtio_register_types) module_dep("hw-display-virtio-gpu"); +module_dep("ui-opengl"); diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index f4e366f64f..5d4bd2b710 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -1536,7 +1536,8 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, .fw_unplugs_cpu = pm->smi_on_cpu_unplug, }; build_cpus_aml(dsdt, machine, opts, pc_madt_cpu_entry, - pm->cpu_hp_io_base, "\\_SB.PCI0", "\\_GPE._E02"); + pm->cpu_hp_io_base, "\\_SB.PCI0", "\\_GPE._E02", + AML_SYSTEM_IO); } if (pcms->memhp_io_base && nr_mem) { diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 37c21a0aec..be0cb39b5c 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -358,7 +358,7 @@ static VTDIOTLBEntry *vtd_lookup_iotlb(IntelIOMMUState *s, uint16_t source_id, { struct vtd_iotlb_key key; VTDIOTLBEntry *entry; - int level; + unsigned level; for (level = VTD_SL_PT_LEVEL; level < VTD_SL_PML4_LEVEL; level++) { key.gfn = vtd_get_iotlb_gfn(addr, level); diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h index f8cf99bddf..5f32c36943 100644 --- a/hw/i386/intel_iommu_internal.h +++ b/hw/i386/intel_iommu_internal.h @@ -264,10 +264,10 @@ #define VTD_FRCD_FR(val) (((val) & 0xffULL) << 32) #define VTD_FRCD_SID_MASK 0xffffULL #define VTD_FRCD_SID(val) ((val) & VTD_FRCD_SID_MASK) +#define VTD_FRCD_PV(val) (((val) & 0xffffULL) << 40) +#define VTD_FRCD_PP(val) (((val) & 0x1ULL) << 31) /* For the low 64-bit of 128-bit */ #define VTD_FRCD_FI(val) ((val) & ~0xfffULL) -#define VTD_FRCD_PV(val) (((val) & 0xffffULL) << 40) -#define VTD_FRCD_PP(val) (((val) & 0x1) << 31) #define VTD_FRCD_IR_IDX(val) (((val) & 0xffffULL) << 48) /* DMA Remapping Fault Conditions */ @@ -436,7 +436,7 @@ struct VTDIOTLBPageInvInfo { uint16_t domain_id; uint32_t pasid; uint64_t addr; - uint8_t mask; + uint64_t mask; }; typedef struct VTDIOTLBPageInvInfo VTDIOTLBPageInvInfo; diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 9445b07b4f..d9e69243b4 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -495,6 +495,7 @@ static void pc_i440fx_machine_9_0_options(MachineClass *m) pc_i440fx_machine_9_1_options(m); m->alias = NULL; m->is_default = false; + m->smbios_memory_device_size = 16 * GiB; compat_props_add(m->compat_props, hw_compat_9_0, hw_compat_9_0_len); compat_props_add(m->compat_props, pc_compat_9_0, pc_compat_9_0_len); diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 71d3c6d122..9d108b194e 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -374,6 +374,7 @@ static void pc_q35_machine_9_0_options(MachineClass *m) PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_q35_machine_9_1_options(m); m->alias = NULL; + m->smbios_memory_device_size = 16 * GiB; compat_props_add(m->compat_props, hw_compat_9_0, hw_compat_9_0_len); compat_props_add(m->compat_props, pc_compat_9_0, pc_compat_9_0_len); pcmc->isa_bios_alias = false; diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c index 35ac59883a..d648192ab9 100644 --- a/hw/mem/cxl_type3.c +++ b/hw/mem/cxl_type3.c @@ -737,6 +737,11 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp) error_setg(errp, "volatile memdev must have backing device"); return false; } + if (host_memory_backend_is_mapped(ct3d->hostvmem)) { + error_setg(errp, "memory backend %s can't be used multiple times.", + object_get_canonical_path_component(OBJECT(ct3d->hostvmem))); + return false; + } memory_region_set_nonvolatile(vmr, false); memory_region_set_enabled(vmr, true); host_memory_backend_set_mapped(ct3d->hostvmem, true); @@ -760,6 +765,11 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp) error_setg(errp, "persistent memdev must have backing device"); return false; } + if (host_memory_backend_is_mapped(ct3d->hostpmem)) { + error_setg(errp, "memory backend %s can't be used multiple times.", + object_get_canonical_path_component(OBJECT(ct3d->hostpmem))); + return false; + } memory_region_set_nonvolatile(pmr, true); memory_region_set_enabled(pmr, true); host_memory_backend_set_mapped(ct3d->hostpmem, true); @@ -790,6 +800,11 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp) return false; } + if (host_memory_backend_is_mapped(ct3d->dc.host_dc)) { + error_setg(errp, "memory backend %s can't be used multiple times.", + object_get_canonical_path_component(OBJECT(ct3d->dc.host_dc))); + return false; + } /* * Set DC regions as volatile for now, non-volatile support can * be added in the future if needed. @@ -829,6 +844,7 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp) uint8_t *pci_conf = pci_dev->config; unsigned short msix_num = 6; int i, rc; + uint16_t count; QTAILQ_INIT(&ct3d->error_list); @@ -893,6 +909,28 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp) } cxl_event_init(&ct3d->cxl_dstate, 2); + /* Set default value for patrol scrub attributes */ + ct3d->patrol_scrub_attrs.scrub_cycle_cap = + CXL_MEMDEV_PS_SCRUB_CYCLE_CHANGE_CAP_DEFAULT | + CXL_MEMDEV_PS_SCRUB_REALTIME_REPORT_CAP_DEFAULT; + ct3d->patrol_scrub_attrs.scrub_cycle = + CXL_MEMDEV_PS_CUR_SCRUB_CYCLE_DEFAULT | + (CXL_MEMDEV_PS_MIN_SCRUB_CYCLE_DEFAULT << 8); + ct3d->patrol_scrub_attrs.scrub_flags = CXL_MEMDEV_PS_ENABLE_DEFAULT; + + /* Set default value for DDR5 ECS read attributes */ + for (count = 0; count < CXL_ECS_NUM_MEDIA_FRUS; count++) { + ct3d->ecs_attrs[count].ecs_log_cap = + CXL_ECS_LOG_ENTRY_TYPE_DEFAULT; + ct3d->ecs_attrs[count].ecs_cap = + CXL_ECS_REALTIME_REPORT_CAP_DEFAULT; + ct3d->ecs_attrs[count].ecs_config = + CXL_ECS_THRESHOLD_COUNT_DEFAULT | + (CXL_ECS_MODE_DEFAULT << 3); + /* Reserved */ + ct3d->ecs_attrs[count].ecs_flags = 0; + } + return; err_release_cdat: @@ -1127,7 +1165,7 @@ MemTxResult cxl_type3_read(PCIDevice *d, hwaddr host_addr, uint64_t *data, return MEMTX_ERROR; } - if (sanitize_running(&ct3d->cci)) { + if (cxl_dev_media_disabled(&ct3d->cxl_dstate)) { qemu_guest_getrandom_nofail(data, size); return MEMTX_OK; } @@ -1149,7 +1187,7 @@ MemTxResult cxl_type3_write(PCIDevice *d, hwaddr host_addr, uint64_t data, return MEMTX_ERROR; } - if (sanitize_running(&ct3d->cci)) { + if (cxl_dev_media_disabled(&ct3d->cxl_dstate)) { return MEMTX_OK; } @@ -1304,6 +1342,12 @@ void cxl_set_poison_list_overflowed(CXLType3Dev *ct3d) cxl_device_get_timestamp(&ct3d->cxl_dstate); } +void cxl_clear_poison_list_overflowed(CXLType3Dev *ct3d) +{ + ct3d->poison_list_overflowed = false; + ct3d->poison_list_overflow_ts = 0; +} + void qmp_cxl_inject_poison(const char *path, uint64_t start, uint64_t length, Error **errp) { @@ -1340,19 +1384,21 @@ void qmp_cxl_inject_poison(const char *path, uint64_t start, uint64_t length, } } - if (ct3d->poison_list_cnt == CXL_POISON_LIST_LIMIT) { - cxl_set_poison_list_overflowed(ct3d); - return; - } - p = g_new0(CXLPoison, 1); p->length = length; p->start = start; /* Different from injected via the mbox */ p->type = CXL_POISON_TYPE_INTERNAL; - QLIST_INSERT_HEAD(&ct3d->poison_list, p, node); - ct3d->poison_list_cnt++; + if (ct3d->poison_list_cnt < CXL_POISON_LIST_LIMIT) { + QLIST_INSERT_HEAD(&ct3d->poison_list, p, node); + ct3d->poison_list_cnt++; + } else { + if (!ct3d->poison_list_overflowed) { + cxl_set_poison_list_overflowed(ct3d); + } + QLIST_INSERT_HEAD(&ct3d->poison_list_bkp, p, node); + } } /* For uncorrectable errors include support for multiple header recording */ diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 18898afe81..a788e6937e 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -48,6 +48,7 @@ static const int kernel_feature_bits[] = { VIRTIO_F_IOMMU_PLATFORM, VIRTIO_F_RING_PACKED, VIRTIO_F_RING_RESET, + VIRTIO_F_IN_ORDER, VIRTIO_F_NOTIFICATION_DATA, VIRTIO_NET_F_HASH_REPORT, VHOST_INVALID_FEATURE_BIT @@ -78,6 +79,7 @@ static const int user_feature_bits[] = { VIRTIO_F_IOMMU_PLATFORM, VIRTIO_F_RING_PACKED, VIRTIO_F_RING_RESET, + VIRTIO_F_IN_ORDER, VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_GUEST_USO4, diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c index 5b1b0cabcf..e86ea2e7ce 100644 --- a/hw/nvme/ctrl.c +++ b/hw/nvme/ctrl.c @@ -203,6 +203,7 @@ #include "sysemu/hostmem.h" #include "hw/pci/msix.h" #include "hw/pci/pcie_sriov.h" +#include "sysemu/spdm-socket.h" #include "migration/vmstate.h" #include "nvme.h" @@ -1758,6 +1759,10 @@ static void nvme_aio_err(NvmeRequest *req, int ret) break; } + if (ret == -ECANCELED) { + status = NVME_CMD_ABORT_REQ; + } + trace_pci_nvme_err_aio(nvme_cid(req), strerror(-ret), status); error_setg_errno(&local_err, -ret, "aio failed"); @@ -2591,6 +2596,7 @@ next: done: iocb->aiocb = NULL; iocb->common.cb(iocb->common.opaque, iocb->ret); + g_free(iocb->range); qemu_aio_unref(iocb); } @@ -2695,6 +2701,7 @@ typedef struct NvmeCopyAIOCB { BlockAIOCB common; BlockAIOCB *aiocb; NvmeRequest *req; + NvmeCtrl *n; int ret; void *ranges; @@ -2713,6 +2720,8 @@ typedef struct NvmeCopyAIOCB { uint64_t slba; NvmeZone *zone; + NvmeNamespace *sns; + uint32_t tcl; } NvmeCopyAIOCB; static void nvme_copy_cancel(BlockAIOCB *aiocb) @@ -2759,13 +2768,19 @@ static void nvme_copy_done(NvmeCopyAIOCB *iocb) static void nvme_do_copy(NvmeCopyAIOCB *iocb); -static void nvme_copy_source_range_parse_format0(void *ranges, int idx, - uint64_t *slba, uint32_t *nlb, - uint16_t *apptag, - uint16_t *appmask, - uint64_t *reftag) +static void nvme_copy_source_range_parse_format0_2(void *ranges, + int idx, uint64_t *slba, + uint32_t *nlb, + uint32_t *snsid, + uint16_t *apptag, + uint16_t *appmask, + uint64_t *reftag) { - NvmeCopySourceRangeFormat0 *_ranges = ranges; + NvmeCopySourceRangeFormat0_2 *_ranges = ranges; + + if (snsid) { + *snsid = le32_to_cpu(_ranges[idx].sparams); + } if (slba) { *slba = le64_to_cpu(_ranges[idx].slba); @@ -2788,13 +2803,19 @@ static void nvme_copy_source_range_parse_format0(void *ranges, int idx, } } -static void nvme_copy_source_range_parse_format1(void *ranges, int idx, - uint64_t *slba, uint32_t *nlb, - uint16_t *apptag, - uint16_t *appmask, - uint64_t *reftag) +static void nvme_copy_source_range_parse_format1_3(void *ranges, int idx, + uint64_t *slba, + uint32_t *nlb, + uint32_t *snsid, + uint16_t *apptag, + uint16_t *appmask, + uint64_t *reftag) { - NvmeCopySourceRangeFormat1 *_ranges = ranges; + NvmeCopySourceRangeFormat1_3 *_ranges = ranges; + + if (snsid) { + *snsid = le32_to_cpu(_ranges[idx].sparams); + } if (slba) { *slba = le64_to_cpu(_ranges[idx].slba); @@ -2826,18 +2847,20 @@ static void nvme_copy_source_range_parse_format1(void *ranges, int idx, static void nvme_copy_source_range_parse(void *ranges, int idx, uint8_t format, uint64_t *slba, uint32_t *nlb, - uint16_t *apptag, uint16_t *appmask, - uint64_t *reftag) + uint32_t *snsid, uint16_t *apptag, + uint16_t *appmask, uint64_t *reftag) { switch (format) { case NVME_COPY_FORMAT_0: - nvme_copy_source_range_parse_format0(ranges, idx, slba, nlb, apptag, - appmask, reftag); + case NVME_COPY_FORMAT_2: + nvme_copy_source_range_parse_format0_2(ranges, idx, slba, nlb, snsid, + apptag, appmask, reftag); break; case NVME_COPY_FORMAT_1: - nvme_copy_source_range_parse_format1(ranges, idx, slba, nlb, apptag, - appmask, reftag); + case NVME_COPY_FORMAT_3: + nvme_copy_source_range_parse_format1_3(ranges, idx, slba, nlb, snsid, + apptag, appmask, reftag); break; default: @@ -2853,10 +2876,10 @@ static inline uint16_t nvme_check_copy_mcl(NvmeNamespace *ns, for (int idx = 0; idx < nr; idx++) { uint32_t nlb; nvme_copy_source_range_parse(iocb->ranges, idx, iocb->format, NULL, - &nlb, NULL, NULL, NULL); + &nlb, NULL, NULL, NULL, NULL); copy_len += nlb; } - + iocb->tcl = copy_len; if (copy_len > ns->id_ns.mcl) { return NVME_CMD_SIZE_LIMIT | NVME_DNR; } @@ -2868,11 +2891,11 @@ static void nvme_copy_out_completed_cb(void *opaque, int ret) { NvmeCopyAIOCB *iocb = opaque; NvmeRequest *req = iocb->req; - NvmeNamespace *ns = req->ns; + NvmeNamespace *dns = req->ns; uint32_t nlb; nvme_copy_source_range_parse(iocb->ranges, iocb->idx, iocb->format, NULL, - &nlb, NULL, NULL, NULL); + &nlb, NULL, NULL, NULL, NULL); if (ret < 0) { iocb->ret = ret; @@ -2881,8 +2904,8 @@ static void nvme_copy_out_completed_cb(void *opaque, int ret) goto out; } - if (ns->params.zoned) { - nvme_advance_zone_wp(ns, iocb->zone, nlb); + if (dns->params.zoned) { + nvme_advance_zone_wp(dns, iocb->zone, nlb); } iocb->idx++; @@ -2895,25 +2918,25 @@ static void nvme_copy_out_cb(void *opaque, int ret) { NvmeCopyAIOCB *iocb = opaque; NvmeRequest *req = iocb->req; - NvmeNamespace *ns = req->ns; + NvmeNamespace *dns = req->ns; uint32_t nlb; size_t mlen; uint8_t *mbounce; - if (ret < 0 || iocb->ret < 0 || !ns->lbaf.ms) { + if (ret < 0 || iocb->ret < 0 || !dns->lbaf.ms) { goto out; } nvme_copy_source_range_parse(iocb->ranges, iocb->idx, iocb->format, NULL, - &nlb, NULL, NULL, NULL); + &nlb, NULL, NULL, NULL, NULL); - mlen = nvme_m2b(ns, nlb); - mbounce = iocb->bounce + nvme_l2b(ns, nlb); + mlen = nvme_m2b(dns, nlb); + mbounce = iocb->bounce + nvme_l2b(dns, nlb); qemu_iovec_reset(&iocb->iov); qemu_iovec_add(&iocb->iov, mbounce, mlen); - iocb->aiocb = blk_aio_pwritev(ns->blkconf.blk, nvme_moff(ns, iocb->slba), + iocb->aiocb = blk_aio_pwritev(dns->blkconf.blk, nvme_moff(dns, iocb->slba), &iocb->iov, 0, nvme_copy_out_completed_cb, iocb); @@ -2927,12 +2950,15 @@ static void nvme_copy_in_completed_cb(void *opaque, int ret) { NvmeCopyAIOCB *iocb = opaque; NvmeRequest *req = iocb->req; - NvmeNamespace *ns = req->ns; + NvmeNamespace *sns = iocb->sns; + NvmeNamespace *dns = req->ns; + NvmeCopyCmd *copy = NULL; + uint8_t *mbounce = NULL; uint32_t nlb; uint64_t slba; uint16_t apptag, appmask; uint64_t reftag; - size_t len; + size_t len, mlen; uint16_t status; if (ret < 0) { @@ -2943,43 +2969,51 @@ static void nvme_copy_in_completed_cb(void *opaque, int ret) } nvme_copy_source_range_parse(iocb->ranges, iocb->idx, iocb->format, &slba, - &nlb, &apptag, &appmask, &reftag); - len = nvme_l2b(ns, nlb); + &nlb, NULL, &apptag, &appmask, &reftag); trace_pci_nvme_copy_out(iocb->slba, nlb); - if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps)) { - NvmeCopyCmd *copy = (NvmeCopyCmd *)&req->cmd; + len = nvme_l2b(sns, nlb); + + if (NVME_ID_NS_DPS_TYPE(sns->id_ns.dps)) { + copy = (NvmeCopyCmd *)&req->cmd; uint16_t prinfor = ((copy->control[0] >> 4) & 0xf); - uint16_t prinfow = ((copy->control[2] >> 2) & 0xf); - size_t mlen = nvme_m2b(ns, nlb); - uint8_t *mbounce = iocb->bounce + nvme_l2b(ns, nlb); + mlen = nvme_m2b(sns, nlb); + mbounce = iocb->bounce + nvme_l2b(sns, nlb); - status = nvme_dif_mangle_mdata(ns, mbounce, mlen, slba); + status = nvme_dif_mangle_mdata(sns, mbounce, mlen, slba); if (status) { goto invalid; } - status = nvme_dif_check(ns, iocb->bounce, len, mbounce, mlen, prinfor, + status = nvme_dif_check(sns, iocb->bounce, len, mbounce, mlen, prinfor, slba, apptag, appmask, &reftag); if (status) { goto invalid; } + } + + if (NVME_ID_NS_DPS_TYPE(dns->id_ns.dps)) { + copy = (NvmeCopyCmd *)&req->cmd; + uint16_t prinfow = ((copy->control[2] >> 2) & 0xf); + + mlen = nvme_m2b(dns, nlb); + mbounce = iocb->bounce + nvme_l2b(dns, nlb); apptag = le16_to_cpu(copy->apptag); appmask = le16_to_cpu(copy->appmask); if (prinfow & NVME_PRINFO_PRACT) { - status = nvme_check_prinfo(ns, prinfow, iocb->slba, iocb->reftag); + status = nvme_check_prinfo(dns, prinfow, iocb->slba, iocb->reftag); if (status) { goto invalid; } - nvme_dif_pract_generate_dif(ns, iocb->bounce, len, mbounce, mlen, + nvme_dif_pract_generate_dif(dns, iocb->bounce, len, mbounce, mlen, apptag, &iocb->reftag); } else { - status = nvme_dif_check(ns, iocb->bounce, len, mbounce, mlen, + status = nvme_dif_check(dns, iocb->bounce, len, mbounce, mlen, prinfow, iocb->slba, apptag, appmask, &iocb->reftag); if (status) { @@ -2988,13 +3022,13 @@ static void nvme_copy_in_completed_cb(void *opaque, int ret) } } - status = nvme_check_bounds(ns, iocb->slba, nlb); + status = nvme_check_bounds(dns, iocb->slba, nlb); if (status) { goto invalid; } - if (ns->params.zoned) { - status = nvme_check_zone_write(ns, iocb->zone, iocb->slba, nlb); + if (dns->params.zoned) { + status = nvme_check_zone_write(dns, iocb->zone, iocb->slba, nlb); if (status) { goto invalid; } @@ -3007,7 +3041,10 @@ static void nvme_copy_in_completed_cb(void *opaque, int ret) qemu_iovec_reset(&iocb->iov); qemu_iovec_add(&iocb->iov, iocb->bounce, len); - iocb->aiocb = blk_aio_pwritev(ns->blkconf.blk, nvme_l2b(ns, iocb->slba), + block_acct_start(blk_get_stats(dns->blkconf.blk), &iocb->acct.write, 0, + BLOCK_ACCT_WRITE); + + iocb->aiocb = blk_aio_pwritev(dns->blkconf.blk, nvme_l2b(dns, iocb->slba), &iocb->iov, 0, nvme_copy_out_cb, iocb); return; @@ -3022,23 +3059,22 @@ out: static void nvme_copy_in_cb(void *opaque, int ret) { NvmeCopyAIOCB *iocb = opaque; - NvmeRequest *req = iocb->req; - NvmeNamespace *ns = req->ns; + NvmeNamespace *sns = iocb->sns; uint64_t slba; uint32_t nlb; - if (ret < 0 || iocb->ret < 0 || !ns->lbaf.ms) { + if (ret < 0 || iocb->ret < 0 || !sns->lbaf.ms) { goto out; } nvme_copy_source_range_parse(iocb->ranges, iocb->idx, iocb->format, &slba, - &nlb, NULL, NULL, NULL); + &nlb, NULL, NULL, NULL, NULL); qemu_iovec_reset(&iocb->iov); - qemu_iovec_add(&iocb->iov, iocb->bounce + nvme_l2b(ns, nlb), - nvme_m2b(ns, nlb)); + qemu_iovec_add(&iocb->iov, iocb->bounce + nvme_l2b(sns, nlb), + nvme_m2b(sns, nlb)); - iocb->aiocb = blk_aio_preadv(ns->blkconf.blk, nvme_moff(ns, slba), + iocb->aiocb = blk_aio_preadv(sns->blkconf.blk, nvme_moff(sns, slba), &iocb->iov, 0, nvme_copy_in_completed_cb, iocb); return; @@ -3047,14 +3083,78 @@ out: nvme_copy_in_completed_cb(iocb, ret); } +static inline bool nvme_csi_supports_copy(uint8_t csi) +{ + return csi == NVME_CSI_NVM || csi == NVME_CSI_ZONED; +} + +static inline bool nvme_copy_ns_format_match(NvmeNamespace *sns, + NvmeNamespace *dns) +{ + return sns->lbaf.ds == dns->lbaf.ds && sns->lbaf.ms == dns->lbaf.ms; +} + +static bool nvme_copy_matching_ns_format(NvmeNamespace *sns, NvmeNamespace *dns, + bool pi_enable) +{ + if (!nvme_csi_supports_copy(sns->csi) || + !nvme_csi_supports_copy(dns->csi)) { + return false; + } + + if (!pi_enable && !nvme_copy_ns_format_match(sns, dns)) { + return false; + } + + if (pi_enable && (!nvme_copy_ns_format_match(sns, dns) || + sns->id_ns.dps != dns->id_ns.dps)) { + return false; + } + + return true; +} + +static inline bool nvme_copy_corresp_pi_match(NvmeNamespace *sns, + NvmeNamespace *dns) +{ + return sns->lbaf.ms == 0 && + ((dns->lbaf.ms == 8 && dns->pif == 0) || + (dns->lbaf.ms == 16 && dns->pif == 1)); +} + +static bool nvme_copy_corresp_pi_format(NvmeNamespace *sns, NvmeNamespace *dns, + bool sns_pi_en) +{ + if (!nvme_csi_supports_copy(sns->csi) || + !nvme_csi_supports_copy(dns->csi)) { + return false; + } + + if (!sns_pi_en && !nvme_copy_corresp_pi_match(sns, dns)) { + return false; + } + + if (sns_pi_en && !nvme_copy_corresp_pi_match(dns, sns)) { + return false; + } + + return true; +} + static void nvme_do_copy(NvmeCopyAIOCB *iocb) { NvmeRequest *req = iocb->req; - NvmeNamespace *ns = req->ns; + NvmeNamespace *sns; + NvmeNamespace *dns = req->ns; + NvmeCopyCmd *copy = (NvmeCopyCmd *)&req->cmd; + uint16_t prinfor = ((copy->control[0] >> 4) & 0xf); + uint16_t prinfow = ((copy->control[2] >> 2) & 0xf); uint64_t slba; uint32_t nlb; size_t len; uint16_t status; + uint32_t dnsid = le32_to_cpu(req->cmd.nsid); + uint32_t snsid = dnsid; if (iocb->ret < 0) { goto done; @@ -3064,40 +3164,124 @@ static void nvme_do_copy(NvmeCopyAIOCB *iocb) goto done; } - nvme_copy_source_range_parse(iocb->ranges, iocb->idx, iocb->format, &slba, - &nlb, NULL, NULL, NULL); - len = nvme_l2b(ns, nlb); + if (iocb->format == 2 || iocb->format == 3) { + nvme_copy_source_range_parse(iocb->ranges, iocb->idx, iocb->format, + &slba, &nlb, &snsid, NULL, NULL, NULL); + if (snsid != dnsid) { + if (snsid == NVME_NSID_BROADCAST || + !nvme_nsid_valid(iocb->n, snsid)) { + status = NVME_INVALID_NSID | NVME_DNR; + goto invalid; + } + iocb->sns = nvme_ns(iocb->n, snsid); + if (unlikely(!iocb->sns)) { + status = NVME_INVALID_FIELD | NVME_DNR; + goto invalid; + } + } else { + if (((slba + nlb) > iocb->slba) && + ((slba + nlb) < (iocb->slba + iocb->tcl))) { + status = NVME_CMD_OVERLAP_IO_RANGE | NVME_DNR; + goto invalid; + } + } + } else { + nvme_copy_source_range_parse(iocb->ranges, iocb->idx, iocb->format, + &slba, &nlb, NULL, NULL, NULL, NULL); + } + + sns = iocb->sns; + if ((snsid == dnsid) && NVME_ID_NS_DPS_TYPE(sns->id_ns.dps) && + ((prinfor & NVME_PRINFO_PRACT) != (prinfow & NVME_PRINFO_PRACT))) { + status = NVME_INVALID_FIELD | NVME_DNR; + goto invalid; + } else if (snsid != dnsid) { + if (!NVME_ID_NS_DPS_TYPE(sns->id_ns.dps) && + !NVME_ID_NS_DPS_TYPE(dns->id_ns.dps)) { + if (!nvme_copy_matching_ns_format(sns, dns, false)) { + status = NVME_CMD_INCOMP_NS_OR_FMT | NVME_DNR; + goto invalid; + } + } + if (NVME_ID_NS_DPS_TYPE(sns->id_ns.dps) && + NVME_ID_NS_DPS_TYPE(dns->id_ns.dps)) { + if ((prinfor & NVME_PRINFO_PRACT) != + (prinfow & NVME_PRINFO_PRACT)) { + status = NVME_CMD_INCOMP_NS_OR_FMT | NVME_DNR; + goto invalid; + } else { + if (!nvme_copy_matching_ns_format(sns, dns, true)) { + status = NVME_CMD_INCOMP_NS_OR_FMT | NVME_DNR; + goto invalid; + } + } + } + + if (!NVME_ID_NS_DPS_TYPE(sns->id_ns.dps) && + NVME_ID_NS_DPS_TYPE(dns->id_ns.dps)) { + if (!(prinfow & NVME_PRINFO_PRACT)) { + status = NVME_CMD_INCOMP_NS_OR_FMT | NVME_DNR; + goto invalid; + } else { + if (!nvme_copy_corresp_pi_format(sns, dns, false)) { + status = NVME_CMD_INCOMP_NS_OR_FMT | NVME_DNR; + goto invalid; + } + } + } + + if (NVME_ID_NS_DPS_TYPE(sns->id_ns.dps) && + !NVME_ID_NS_DPS_TYPE(dns->id_ns.dps)) { + if (!(prinfor & NVME_PRINFO_PRACT)) { + status = NVME_CMD_INCOMP_NS_OR_FMT | NVME_DNR; + goto invalid; + } else { + if (!nvme_copy_corresp_pi_format(sns, dns, true)) { + status = NVME_CMD_INCOMP_NS_OR_FMT | NVME_DNR; + goto invalid; + } + } + } + } + len = nvme_l2b(sns, nlb); trace_pci_nvme_copy_source_range(slba, nlb); - if (nlb > le16_to_cpu(ns->id_ns.mssrl)) { + if (nlb > le16_to_cpu(sns->id_ns.mssrl)) { status = NVME_CMD_SIZE_LIMIT | NVME_DNR; goto invalid; } - status = nvme_check_bounds(ns, slba, nlb); + status = nvme_check_bounds(sns, slba, nlb); if (status) { goto invalid; } - if (NVME_ERR_REC_DULBE(ns->features.err_rec)) { - status = nvme_check_dulbe(ns, slba, nlb); + if (NVME_ERR_REC_DULBE(sns->features.err_rec)) { + status = nvme_check_dulbe(sns, slba, nlb); if (status) { goto invalid; } } - if (ns->params.zoned) { - status = nvme_check_zone_read(ns, slba, nlb); + if (sns->params.zoned) { + status = nvme_check_zone_read(sns, slba, nlb); if (status) { goto invalid; } } + g_free(iocb->bounce); + iocb->bounce = g_malloc_n(le16_to_cpu(sns->id_ns.mssrl), + sns->lbasz + sns->lbaf.ms); + qemu_iovec_reset(&iocb->iov); qemu_iovec_add(&iocb->iov, iocb->bounce, len); - iocb->aiocb = blk_aio_preadv(ns->blkconf.blk, nvme_l2b(ns, slba), + block_acct_start(blk_get_stats(sns->blkconf.blk), &iocb->acct.read, 0, + BLOCK_ACCT_READ); + + iocb->aiocb = blk_aio_preadv(sns->blkconf.blk, nvme_l2b(sns, slba), &iocb->iov, 0, nvme_copy_in_cb, iocb); return; @@ -3116,9 +3300,7 @@ static uint16_t nvme_copy(NvmeCtrl *n, NvmeRequest *req) nvme_misc_cb, req); uint16_t nr = copy->nr + 1; uint8_t format = copy->control[0] & 0xf; - uint16_t prinfor = ((copy->control[0] >> 4) & 0xf); - uint16_t prinfow = ((copy->control[2] >> 2) & 0xf); - size_t len = sizeof(NvmeCopySourceRangeFormat0); + size_t len = sizeof(NvmeCopySourceRangeFormat0_2); uint16_t status; @@ -3127,13 +3309,9 @@ static uint16_t nvme_copy(NvmeCtrl *n, NvmeRequest *req) iocb->ranges = NULL; iocb->zone = NULL; - if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) && - ((prinfor & NVME_PRINFO_PRACT) != (prinfow & NVME_PRINFO_PRACT))) { - status = NVME_INVALID_FIELD | NVME_DNR; - goto invalid; - } - - if (!(n->id_ctrl.ocfs & (1 << format))) { + if (!(n->id_ctrl.ocfs & (1 << format)) || + ((format == 2 || format == 3) && + !(n->features.hbs.cdfe & (1 << format)))) { trace_pci_nvme_err_copy_invalid_format(format); status = NVME_INVALID_FIELD | NVME_DNR; goto invalid; @@ -3144,14 +3322,14 @@ static uint16_t nvme_copy(NvmeCtrl *n, NvmeRequest *req) goto invalid; } - if ((ns->pif == 0x0 && format != 0x0) || - (ns->pif != 0x0 && format != 0x1)) { + if ((ns->pif == 0x0 && (format != 0x0 && format != 0x2)) || + (ns->pif != 0x0 && (format != 0x1 && format != 0x3))) { status = NVME_INVALID_FORMAT | NVME_DNR; goto invalid; } if (ns->pif) { - len = sizeof(NvmeCopySourceRangeFormat1); + len = sizeof(NvmeCopySourceRangeFormat1_3); } iocb->format = format; @@ -3187,17 +3365,13 @@ static uint16_t nvme_copy(NvmeCtrl *n, NvmeRequest *req) iocb->idx = 0; iocb->reftag = le32_to_cpu(copy->reftag); iocb->reftag |= (uint64_t)le32_to_cpu(copy->cdw3) << 32; - iocb->bounce = g_malloc_n(le16_to_cpu(ns->id_ns.mssrl), - ns->lbasz + ns->lbaf.ms); qemu_iovec_init(&iocb->iov, 1); - block_acct_start(blk_get_stats(ns->blkconf.blk), &iocb->acct.read, 0, - BLOCK_ACCT_READ); - block_acct_start(blk_get_stats(ns->blkconf.blk), &iocb->acct.write, 0, - BLOCK_ACCT_WRITE); - req->aiocb = &iocb->common; + iocb->sns = req->ns; + iocb->n = n; + iocb->bounce = NULL; nvme_do_copy(iocb); return NVME_NO_COMPLETE; @@ -4167,7 +4341,7 @@ static bool nvme_zone_matches_filter(uint32_t zafs, NvmeZone *zl) static uint16_t nvme_zone_mgmt_recv(NvmeCtrl *n, NvmeRequest *req) { - NvmeCmd *cmd = (NvmeCmd *)&req->cmd; + NvmeCmd *cmd = &req->cmd; NvmeNamespace *ns = req->ns; /* cdw12 is zero-based number of dwords to return. Convert to bytes */ uint32_t data_size = (le32_to_cpu(cmd->cdw12) + 1) << 2; @@ -4406,10 +4580,6 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_io_cmd(nvme_cid(req), nsid, nvme_sqid(req), req->cmd.opcode, nvme_io_opc_str(req->cmd.opcode)); - if (!nvme_nsid_valid(n, nsid)) { - return NVME_INVALID_NSID | NVME_DNR; - } - /* * In the base NVM command set, Flush may apply to all namespaces * (indicated by NSID being set to FFFFFFFFh). But if that feature is used @@ -4429,10 +4599,15 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) * device only supports namespace types that includes the NVM Flush command * (NVM and Zoned), so always do an NVM Flush. */ + if (req->cmd.opcode == NVME_CMD_FLUSH) { return nvme_flush(n, req); } + if (!nvme_nsid_valid(n, nsid) || nsid == NVME_NSID_BROADCAST) { + return NVME_INVALID_NSID | NVME_DNR; + } + ns = nvme_ns(n, nsid); if (unlikely(!ns)) { return NVME_INVALID_FIELD | NVME_DNR; @@ -5780,12 +5955,40 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req) static uint16_t nvme_abort(NvmeCtrl *n, NvmeRequest *req) { uint16_t sqid = le32_to_cpu(req->cmd.cdw10) & 0xffff; + uint16_t cid = (le32_to_cpu(req->cmd.cdw10) >> 16) & 0xffff; + NvmeSQueue *sq = n->sq[sqid]; + NvmeRequest *r, *next; + int i; req->cqe.result = 1; if (nvme_check_sqid(n, sqid)) { return NVME_INVALID_FIELD | NVME_DNR; } + if (sqid == 0) { + for (i = 0; i < n->outstanding_aers; i++) { + NvmeRequest *re = n->aer_reqs[i]; + if (re->cqe.cid == cid) { + memmove(n->aer_reqs + i, n->aer_reqs + i + 1, + (n->outstanding_aers - i - 1) * sizeof(NvmeRequest *)); + n->outstanding_aers--; + re->status = NVME_CMD_ABORT_REQ; + req->cqe.result = 0; + nvme_enqueue_req_completion(&n->admin_cq, re); + return NVME_SUCCESS; + } + } + } + + QTAILQ_FOREACH_SAFE(r, &sq->out_req_list, entry, next) { + if (r->cqe.cid == cid) { + if (r->aiocb) { + blk_aio_cancel_async(r->aiocb); + } + break; + } + } + return NVME_SUCCESS; } @@ -8113,6 +8316,27 @@ static int nvme_add_pm_capability(PCIDevice *pci_dev, uint8_t offset) return 0; } +static bool pcie_doe_spdm_rsp(DOECap *doe_cap) +{ + void *req = pcie_doe_get_write_mbox_ptr(doe_cap); + uint32_t req_len = pcie_doe_get_obj_len(req) * 4; + void *rsp = doe_cap->read_mbox; + uint32_t rsp_len = SPDM_SOCKET_MAX_MESSAGE_BUFFER_SIZE; + + uint32_t recvd = spdm_socket_rsp(doe_cap->spdm_socket, + SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE, + req, req_len, rsp, rsp_len); + doe_cap->read_mbox_len += DIV_ROUND_UP(recvd, 4); + + return recvd != 0; +} + +static DOEProtocol doe_spdm_prot[] = { + { PCI_VENDOR_ID_PCI_SIG, PCI_SIG_DOE_CMA, pcie_doe_spdm_rsp }, + { PCI_VENDOR_ID_PCI_SIG, PCI_SIG_DOE_SECURED_CMA, pcie_doe_spdm_rsp }, + { } +}; + static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp) { ERRP_GUARD(); @@ -8200,6 +8424,25 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp) nvme_update_msixcap_ts(pci_dev, n->conf_msix_qsize); + pcie_cap_deverr_init(pci_dev); + + /* DOE Initialisation */ + if (pci_dev->spdm_port) { + uint16_t doe_offset = n->params.sriov_max_vfs ? + PCI_CONFIG_SPACE_SIZE + PCI_ARI_SIZEOF + : PCI_CONFIG_SPACE_SIZE; + + pcie_doe_init(pci_dev, &pci_dev->doe_spdm, doe_offset, + doe_spdm_prot, true, 0); + + pci_dev->doe_spdm.spdm_socket = spdm_socket_connect(pci_dev->spdm_port, + errp); + + if (pci_dev->doe_spdm.spdm_socket < 0) { + return false; + } + } + if (n->params.cmb_size_mb) { nvme_init_cmb(n, pci_dev); } @@ -8287,7 +8530,8 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->nn = cpu_to_le32(NVME_MAX_NAMESPACES); id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROES | NVME_ONCS_TIMESTAMP | NVME_ONCS_FEATURES | NVME_ONCS_DSM | - NVME_ONCS_COMPARE | NVME_ONCS_COPY); + NVME_ONCS_COMPARE | NVME_ONCS_COPY | + NVME_ONCS_NVMCSA | NVME_ONCS_NVMAFC); /* * NOTE: If this device ever supports a command set that does NOT use 0x0 @@ -8298,7 +8542,8 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) */ id->vwc = NVME_VWC_NSID_BROADCAST_SUPPORT | NVME_VWC_PRESENT; - id->ocfs = cpu_to_le16(NVME_OCFS_COPY_FORMAT_0 | NVME_OCFS_COPY_FORMAT_1); + id->ocfs = cpu_to_le16(NVME_OCFS_COPY_FORMAT_0 | NVME_OCFS_COPY_FORMAT_1 | + NVME_OCFS_COPY_FORMAT_2 | NVME_OCFS_COPY_FORMAT_3); id->sgls = cpu_to_le32(NVME_CTRL_SGLS_SUPPORT_NO_ALIGN); nvme_init_subnqn(n); @@ -8446,6 +8691,11 @@ static void nvme_exit(PCIDevice *pci_dev) g_free(n->cmb.buf); } + if (pci_dev->doe_spdm.spdm_socket > 0) { + spdm_socket_close(pci_dev->doe_spdm.spdm_socket, + SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE); + } + if (n->pmr.dev) { host_memory_backend_set_mapped(n->pmr.dev, false); } @@ -8491,6 +8741,7 @@ static Property nvme_props[] = { DEFINE_PROP_BOOL("msix-exclusive-bar", NvmeCtrl, params.msix_exclusive_bar, false), DEFINE_PROP_UINT16("mqes", NvmeCtrl, params.mqes, 0x7ff), + DEFINE_PROP_UINT16("spdm_port", PCIDevice, spdm_port, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -8562,11 +8813,25 @@ static void nvme_pci_write_config(PCIDevice *dev, uint32_t address, { uint16_t old_num_vfs = pcie_sriov_num_vfs(dev); + if (pcie_find_capability(dev, PCI_EXT_CAP_ID_DOE)) { + pcie_doe_write_config(&dev->doe_spdm, address, val, len); + } pci_default_write_config(dev, address, val, len); pcie_cap_flr_write_config(dev, address, val, len); nvme_sriov_post_write_config(dev, old_num_vfs); } +static uint32_t nvme_pci_read_config(PCIDevice *dev, uint32_t address, int len) +{ + uint32_t val; + if (dev->spdm_port && pcie_find_capability(dev, PCI_EXT_CAP_ID_DOE)) { + if (pcie_doe_read_config(&dev->doe_spdm, address, len, &val)) { + return val; + } + } + return pci_default_read_config(dev, address, len); +} + static const VMStateDescription nvme_vmstate = { .name = "nvme", .unmigratable = 1, @@ -8579,6 +8844,7 @@ static void nvme_class_init(ObjectClass *oc, void *data) pc->realize = nvme_realize; pc->config_write = nvme_pci_write_config; + pc->config_read = nvme_pci_read_config; pc->exit = nvme_exit; pc->class_id = PCI_CLASS_STORAGE_EXPRESS; pc->revision = 2; diff --git a/hw/pci-host/gpex-acpi.c b/hw/pci-host/gpex-acpi.c index f69413ea2c..391fabb8a8 100644 --- a/hw/pci-host/gpex-acpi.c +++ b/hw/pci-host/gpex-acpi.c @@ -7,7 +7,8 @@ #include "hw/pci/pcie_host.h" #include "hw/acpi/cxl.h" -static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq) +static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq, + Aml *scope, uint8_t bus_num) { Aml *method, *crs; int i, slot_no; @@ -20,7 +21,7 @@ static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq) Aml *pkg = aml_package(4); aml_append(pkg, aml_int((slot_no << 16) | 0xFFFF)); aml_append(pkg, aml_int(i)); - aml_append(pkg, aml_name("GSI%d", gsi)); + aml_append(pkg, aml_name("L%.02X%X", bus_num, gsi)); aml_append(pkg, aml_int(0)); aml_append(rt_pkg, pkg); } @@ -30,7 +31,7 @@ static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq) /* Create GSI link device */ for (i = 0; i < PCI_NUM_PINS; i++) { uint32_t irqs = irq + i; - Aml *dev_gsi = aml_device("GSI%d", i); + Aml *dev_gsi = aml_device("L%.02X%X", bus_num, i); aml_append(dev_gsi, aml_name_decl("_HID", aml_string("PNP0C0F"))); aml_append(dev_gsi, aml_name_decl("_UID", aml_int(i))); crs = aml_resource_template(); @@ -45,7 +46,7 @@ static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq) aml_append(dev_gsi, aml_name_decl("_CRS", crs)); method = aml_method("_SRS", 1, AML_NOTSERIALIZED); aml_append(dev_gsi, method); - aml_append(dev, dev_gsi); + aml_append(scope, dev_gsi); } } @@ -174,7 +175,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg) aml_append(dev, aml_name_decl("_PXM", aml_int(numa_node))); } - acpi_dsdt_add_pci_route_table(dev, cfg->irq); + acpi_dsdt_add_pci_route_table(dev, cfg->irq, scope, bus_num); /* * Resources defined for PXBs are composed of the following parts: @@ -205,7 +206,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg) aml_append(dev, aml_name_decl("_STR", aml_unicode("PCIe 0 Device"))); aml_append(dev, aml_name_decl("_CCA", aml_int(1))); - acpi_dsdt_add_pci_route_table(dev, cfg->irq); + acpi_dsdt_add_pci_route_table(dev, cfg->irq, scope, 0); method = aml_method("_CBA", 0, AML_NOTSERIALIZED); aml_append(method, aml_return(aml_int(cfg->ecam.base))); diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 4c7be52951..8ad5d7e2d8 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -85,6 +85,7 @@ static Property pci_props[] = { QEMU_PCIE_ERR_UNC_MASK_BITNR, true), DEFINE_PROP_BIT("x-pcie-ari-nextfn-1", PCIDevice, cap_present, QEMU_PCIE_ARI_NEXTFN_1_BITNR, false), + DEFINE_PROP_STRING("sriov-pf", PCIDevice, sriov_pf), DEFINE_PROP_END_OF_LIST() }; @@ -959,13 +960,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp) dev->config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION; } - /* - * With SR/IOV and ARI, a device at function 0 need not be a multifunction - * device, as it may just be a VF that ended up with function 0 in - * the legacy PCI interpretation. Avoid failing in such cases: - */ - if (pci_is_vf(dev) && - dev->exp.sriov_vf.pf->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) { + /* SR/IOV is not handled here. */ + if (pci_is_vf(dev)) { return; } @@ -998,7 +994,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp) } /* function 0 indicates single function, so function > 0 must be NULL */ for (func = 1; func < PCI_FUNC_MAX; ++func) { - if (bus->devices[PCI_DEVFN(slot, func)]) { + PCIDevice *device = bus->devices[PCI_DEVFN(slot, func)]; + if (device && !pci_is_vf(device)) { error_setg(errp, "PCI: %x.0 indicates single function, " "but %x.%x is already populated.", slot, slot, func); @@ -1283,6 +1280,7 @@ static void pci_qdev_unrealize(DeviceState *dev) pci_unregister_io_regions(pci_dev); pci_del_option_rom(pci_dev); + pcie_sriov_unregister_device(pci_dev); if (pc->exit) { pc->exit(pci_dev); @@ -1314,7 +1312,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, pcibus_t size = memory_region_size(memory); uint8_t hdr_type; - assert(!pci_is_vf(pci_dev)); /* VFs must use pcie_sriov_vf_register_bar */ assert(region_num >= 0); assert(region_num < PCI_NUM_REGIONS); assert(is_power_of_2(size)); @@ -1325,7 +1322,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, assert(hdr_type != PCI_HEADER_TYPE_BRIDGE || region_num < 2); r = &pci_dev->io_regions[region_num]; - r->addr = PCI_BAR_UNMAPPED; r->size = size; r->type = type; r->memory = memory; @@ -1333,22 +1329,35 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, ? pci_get_bus(pci_dev)->address_space_io : pci_get_bus(pci_dev)->address_space_mem; - wmask = ~(size - 1); - if (region_num == PCI_ROM_SLOT) { - /* ROM enable bit is writable */ - wmask |= PCI_ROM_ADDRESS_ENABLE; - } - - addr = pci_bar(pci_dev, region_num); - pci_set_long(pci_dev->config + addr, type); + if (pci_is_vf(pci_dev)) { + PCIDevice *pf = pci_dev->exp.sriov_vf.pf; + assert(!pf || type == pf->exp.sriov_pf.vf_bar_type[region_num]); - if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) && - r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) { - pci_set_quad(pci_dev->wmask + addr, wmask); - pci_set_quad(pci_dev->cmask + addr, ~0ULL); + r->addr = pci_bar_address(pci_dev, region_num, r->type, r->size); + if (r->addr != PCI_BAR_UNMAPPED) { + memory_region_add_subregion_overlap(r->address_space, + r->addr, r->memory, 1); + } } else { - pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff); - pci_set_long(pci_dev->cmask + addr, 0xffffffff); + r->addr = PCI_BAR_UNMAPPED; + + wmask = ~(size - 1); + if (region_num == PCI_ROM_SLOT) { + /* ROM enable bit is writable */ + wmask |= PCI_ROM_ADDRESS_ENABLE; + } + + addr = pci_bar(pci_dev, region_num); + pci_set_long(pci_dev->config + addr, type); + + if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) && + r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) { + pci_set_quad(pci_dev->wmask + addr, wmask); + pci_set_quad(pci_dev->cmask + addr, ~0ULL); + } else { + pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff); + pci_set_long(pci_dev->cmask + addr, 0xffffffff); + } } } @@ -1437,7 +1446,11 @@ static pcibus_t pci_config_get_bar_addr(PCIDevice *d, int reg, pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_OFFSET); uint16_t vf_stride = pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_STRIDE); - uint32_t vf_num = (d->devfn - (pf->devfn + vf_offset)) / vf_stride; + uint32_t vf_num = d->devfn - (pf->devfn + vf_offset); + + if (vf_num) { + vf_num /= vf_stride; + } if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) { new_addr = pci_get_quad(pf->config + bar); @@ -2105,6 +2118,11 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp) } } + if (!pcie_sriov_register_device(pci_dev, errp)) { + pci_qdev_unrealize(DEVICE(pci_dev)); + return; + } + /* * A PCIe Downstream Port that do not have ARI Forwarding enabled must * associate only Device 0 with the device attached to the bus diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c index 56523ab4e8..0fc9f810b9 100644 --- a/hw/pci/pcie_sriov.c +++ b/hw/pci/pcie_sriov.c @@ -20,6 +20,8 @@ #include "qapi/error.h" #include "trace.h" +static GHashTable *pfs; + static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs) { for (uint16_t i = 0; i < total_vfs; i++) { @@ -31,17 +33,62 @@ static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs) dev->exp.sriov_pf.vf = NULL; } -bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, - const char *vfname, uint16_t vf_dev_id, - uint16_t init_vfs, uint16_t total_vfs, - uint16_t vf_offset, uint16_t vf_stride, - Error **errp) +static void clear_ctrl_vfe(PCIDevice *dev) +{ + uint8_t *ctrl = dev->config + dev->exp.sriov_cap + PCI_SRIOV_CTRL; + pci_set_word(ctrl, pci_get_word(ctrl) & ~PCI_SRIOV_CTRL_VFE); +} + +static void register_vfs(PCIDevice *dev) +{ + uint16_t num_vfs; + uint16_t i; + uint16_t sriov_cap = dev->exp.sriov_cap; + + assert(sriov_cap > 0); + num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF); + if (num_vfs > pci_get_word(dev->config + sriov_cap + PCI_SRIOV_TOTAL_VF)) { + clear_ctrl_vfe(dev); + return; + } + + trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn), + PCI_FUNC(dev->devfn), num_vfs); + for (i = 0; i < num_vfs; i++) { + pci_set_enabled(dev->exp.sriov_pf.vf[i], true); + } +} + +static void unregister_vfs(PCIDevice *dev) +{ + uint16_t i; + uint8_t *cfg = dev->config + dev->exp.sriov_cap; + + trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn), + PCI_FUNC(dev->devfn)); + for (i = 0; i < pci_get_word(cfg + PCI_SRIOV_TOTAL_VF); i++) { + pci_set_enabled(dev->exp.sriov_pf.vf[i], false); + } +} + +static bool pcie_sriov_pf_init_common(PCIDevice *dev, uint16_t offset, + uint16_t vf_dev_id, uint16_t init_vfs, + uint16_t total_vfs, uint16_t vf_offset, + uint16_t vf_stride, Error **errp) { - BusState *bus = qdev_get_parent_bus(&dev->qdev); - int32_t devfn = dev->devfn + vf_offset; uint8_t *cfg = dev->config + offset; uint8_t *wmask; + if (!pci_is_express(dev)) { + error_setg(errp, "PCI Express is required for SR-IOV PF"); + return false; + } + + if (pci_is_vf(dev)) { + error_setg(errp, "a device cannot be both an SR-IOV PF and a VF"); + return false; + } + if (total_vfs) { uint16_t ari_cap = pcie_find_capability(dev, PCI_EXT_CAP_ID_ARI); uint16_t first_vf_devfn = dev->devfn + vf_offset; @@ -90,6 +137,28 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, qdev_prop_set_bit(&dev->qdev, "multifunction", true); + return true; +} + +bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, + const char *vfname, uint16_t vf_dev_id, + uint16_t init_vfs, uint16_t total_vfs, + uint16_t vf_offset, uint16_t vf_stride, + Error **errp) +{ + BusState *bus = qdev_get_parent_bus(&dev->qdev); + int32_t devfn = dev->devfn + vf_offset; + + if (pfs && g_hash_table_contains(pfs, dev->qdev.id)) { + error_setg(errp, "attaching user-created SR-IOV VF unsupported"); + return false; + } + + if (!pcie_sriov_pf_init_common(dev, offset, vf_dev_id, init_vfs, + total_vfs, vf_offset, vf_stride, errp)) { + return false; + } + dev->exp.sriov_pf.vf = g_new(PCIDevice *, total_vfs); for (uint16_t i = 0; i < total_vfs; i++) { @@ -119,7 +188,24 @@ void pcie_sriov_pf_exit(PCIDevice *dev) { uint8_t *cfg = dev->config + dev->exp.sriov_cap; - unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF)); + if (dev->exp.sriov_pf.vf_user_created) { + uint16_t ven_id = pci_get_word(dev->config + PCI_VENDOR_ID); + uint16_t total_vfs = pci_get_word(dev->config + PCI_SRIOV_TOTAL_VF); + uint16_t vf_dev_id = pci_get_word(dev->config + PCI_SRIOV_VF_DID); + + unregister_vfs(dev); + + for (uint16_t i = 0; i < total_vfs; i++) { + PCIDevice *vf = dev->exp.sriov_pf.vf[i]; + + vf->exp.sriov_vf.pf = NULL; + + pci_config_set_vendor_id(vf->config, ven_id); + pci_config_set_device_id(vf->config, vf_dev_id); + } + } else { + unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF)); + } } void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, @@ -152,74 +238,172 @@ void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num, MemoryRegion *memory) { - PCIIORegion *r; - PCIBus *bus = pci_get_bus(dev); uint8_t type; - pcibus_t size = memory_region_size(memory); - assert(pci_is_vf(dev)); /* PFs must use pci_register_bar */ - assert(region_num >= 0); - assert(region_num < PCI_NUM_REGIONS); + assert(dev->exp.sriov_vf.pf); type = dev->exp.sriov_vf.pf->exp.sriov_pf.vf_bar_type[region_num]; - if (!is_power_of_2(size)) { - error_report("%s: PCI region size must be a power" - " of two - type=0x%x, size=0x%"FMT_PCIBUS, - __func__, type, size); - exit(1); - } - - r = &dev->io_regions[region_num]; - r->memory = memory; - r->address_space = - type & PCI_BASE_ADDRESS_SPACE_IO - ? bus->address_space_io - : bus->address_space_mem; - r->size = size; - r->type = type; - - r->addr = pci_bar_address(dev, region_num, r->type, r->size); - if (r->addr != PCI_BAR_UNMAPPED) { - memory_region_add_subregion_overlap(r->address_space, - r->addr, r->memory, 1); - } + return pci_register_bar(dev, region_num, type, memory); } -static void clear_ctrl_vfe(PCIDevice *dev) +static gint compare_vf_devfns(gconstpointer a, gconstpointer b) { - uint8_t *ctrl = dev->config + dev->exp.sriov_cap + PCI_SRIOV_CTRL; - pci_set_word(ctrl, pci_get_word(ctrl) & ~PCI_SRIOV_CTRL_VFE); + return (*(PCIDevice **)a)->devfn - (*(PCIDevice **)b)->devfn; } -static void register_vfs(PCIDevice *dev) +int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev, + uint16_t offset, + Error **errp) { - uint16_t num_vfs; + GPtrArray *pf; + PCIDevice **vfs; + BusState *bus = qdev_get_parent_bus(DEVICE(dev)); + uint16_t ven_id = pci_get_word(dev->config + PCI_VENDOR_ID); + uint16_t vf_dev_id; + uint16_t vf_offset; + uint16_t vf_stride; uint16_t i; - uint16_t sriov_cap = dev->exp.sriov_cap; - assert(sriov_cap > 0); - num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF); - if (num_vfs > pci_get_word(dev->config + sriov_cap + PCI_SRIOV_TOTAL_VF)) { - clear_ctrl_vfe(dev); - return; + if (!pfs || !dev->qdev.id) { + return 0; } - trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn), - PCI_FUNC(dev->devfn), num_vfs); - for (i = 0; i < num_vfs; i++) { - pci_set_enabled(dev->exp.sriov_pf.vf[i], true); + pf = g_hash_table_lookup(pfs, dev->qdev.id); + if (!pf) { + return 0; } + + if (pf->len > UINT16_MAX) { + error_setg(errp, "too many VFs"); + return -1; + } + + g_ptr_array_sort(pf, compare_vf_devfns); + vfs = (void *)pf->pdata; + + if (vfs[0]->devfn <= dev->devfn) { + error_setg(errp, "a VF function number is less than the PF function number"); + return -1; + } + + vf_dev_id = pci_get_word(vfs[0]->config + PCI_DEVICE_ID); + vf_offset = vfs[0]->devfn - dev->devfn; + vf_stride = pf->len < 2 ? 0 : vfs[1]->devfn - vfs[0]->devfn; + + for (i = 0; i < pf->len; i++) { + if (bus != qdev_get_parent_bus(&vfs[i]->qdev)) { + error_setg(errp, "SR-IOV VF parent bus mismatches with PF"); + return -1; + } + + if (ven_id != pci_get_word(vfs[i]->config + PCI_VENDOR_ID)) { + error_setg(errp, "SR-IOV VF vendor ID mismatches with PF"); + return -1; + } + + if (vf_dev_id != pci_get_word(vfs[i]->config + PCI_DEVICE_ID)) { + error_setg(errp, "inconsistent SR-IOV VF device IDs"); + return -1; + } + + for (size_t j = 0; j < PCI_NUM_REGIONS; j++) { + if (vfs[i]->io_regions[j].size != vfs[0]->io_regions[j].size || + vfs[i]->io_regions[j].type != vfs[0]->io_regions[j].type) { + error_setg(errp, "inconsistent SR-IOV BARs"); + return -1; + } + } + + if (vfs[i]->devfn - vfs[0]->devfn != vf_stride * i) { + error_setg(errp, "inconsistent SR-IOV stride"); + return -1; + } + } + + if (!pcie_sriov_pf_init_common(dev, offset, vf_dev_id, pf->len, + pf->len, vf_offset, vf_stride, errp)) { + return -1; + } + + for (i = 0; i < pf->len; i++) { + vfs[i]->exp.sriov_vf.pf = dev; + vfs[i]->exp.sriov_vf.vf_number = i; + + /* set vid/did according to sr/iov spec - they are not used */ + pci_config_set_vendor_id(vfs[i]->config, 0xffff); + pci_config_set_device_id(vfs[i]->config, 0xffff); + } + + dev->exp.sriov_pf.vf = vfs; + dev->exp.sriov_pf.vf_user_created = true; + + for (i = 0; i < PCI_NUM_REGIONS; i++) { + PCIIORegion *region = &vfs[0]->io_regions[i]; + + if (region->size) { + pcie_sriov_pf_init_vf_bar(dev, i, region->type, region->size); + } + } + + return PCI_EXT_CAP_SRIOV_SIZEOF; } -static void unregister_vfs(PCIDevice *dev) +bool pcie_sriov_register_device(PCIDevice *dev, Error **errp) { - uint16_t i; - uint8_t *cfg = dev->config + dev->exp.sriov_cap; + if (!dev->exp.sriov_pf.vf && dev->qdev.id && + pfs && g_hash_table_contains(pfs, dev->qdev.id)) { + error_setg(errp, "attaching user-created SR-IOV VF unsupported"); + return false; + } - trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn), - PCI_FUNC(dev->devfn)); - for (i = 0; i < pci_get_word(cfg + PCI_SRIOV_TOTAL_VF); i++) { - pci_set_enabled(dev->exp.sriov_pf.vf[i], false); + if (dev->sriov_pf) { + PCIDevice *pci_pf; + GPtrArray *pf; + + if (!PCI_DEVICE_GET_CLASS(dev)->sriov_vf_user_creatable) { + error_setg(errp, "user cannot create SR-IOV VF with this device type"); + return false; + } + + if (!pci_is_express(dev)) { + error_setg(errp, "PCI Express is required for SR-IOV VF"); + return false; + } + + if (!pci_qdev_find_device(dev->sriov_pf, &pci_pf)) { + error_setg(errp, "PCI device specified as SR-IOV PF already exists"); + return false; + } + + if (!pfs) { + pfs = g_hash_table_new_full(g_str_hash, g_str_equal, g_free, NULL); + } + + pf = g_hash_table_lookup(pfs, dev->sriov_pf); + if (!pf) { + pf = g_ptr_array_new(); + g_hash_table_insert(pfs, g_strdup(dev->sriov_pf), pf); + } + + g_ptr_array_add(pf, dev); + } + + return true; +} + +void pcie_sriov_unregister_device(PCIDevice *dev) +{ + if (dev->sriov_pf && pfs) { + GPtrArray *pf = g_hash_table_lookup(pfs, dev->sriov_pf); + + if (pf) { + g_ptr_array_remove_fast(pf, dev); + + if (!pf->len) { + g_hash_table_remove(pfs, dev->sriov_pf); + g_ptr_array_free(pf, FALSE); + } + } } } @@ -306,7 +490,7 @@ void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize) uint16_t pcie_sriov_vf_number(PCIDevice *dev) { - assert(pci_is_vf(dev)); + assert(dev->exp.sriov_vf.pf); return dev->exp.sriov_vf.vf_number; } diff --git a/hw/riscv/virt-acpi-build.c b/hw/riscv/virt-acpi-build.c index 0925528160..36d6a3a412 100644 --- a/hw/riscv/virt-acpi-build.c +++ b/hw/riscv/virt-acpi-build.c @@ -141,12 +141,36 @@ static void acpi_dsdt_add_cpus(Aml *scope, RISCVVirtState *s) } } +static void acpi_dsdt_add_plic_aplic(Aml *scope, uint8_t socket_count, + uint64_t mmio_base, uint64_t mmio_size, + const char *hid) +{ + uint64_t plic_aplic_addr; + uint32_t gsi_base; + uint8_t socket; + + for (socket = 0; socket < socket_count; socket++) { + plic_aplic_addr = mmio_base + mmio_size * socket; + gsi_base = VIRT_IRQCHIP_NUM_SOURCES * socket; + Aml *dev = aml_device("IC%.02X", socket); + aml_append(dev, aml_name_decl("_HID", aml_string("%s", hid))); + aml_append(dev, aml_name_decl("_UID", aml_int(socket))); + aml_append(dev, aml_name_decl("_GSB", aml_int(gsi_base))); + + Aml *crs = aml_resource_template(); + aml_append(crs, aml_memory32_fixed(plic_aplic_addr, mmio_size, + AML_READ_WRITE)); + aml_append(dev, aml_name_decl("_CRS", crs)); + aml_append(scope, dev); + } +} + static void acpi_dsdt_add_uart(Aml *scope, const MemMapEntry *uart_memmap, uint32_t uart_irq) { Aml *dev = aml_device("COM0"); - aml_append(dev, aml_name_decl("_HID", aml_string("PNP0501"))); + aml_append(dev, aml_name_decl("_HID", aml_string("RSCV0003"))); aml_append(dev, aml_name_decl("_UID", aml_int(0))); Aml *crs = aml_resource_template(); @@ -411,6 +435,14 @@ static void build_dsdt(GArray *table_data, socket_count = riscv_socket_count(ms); + if (s->aia_type == VIRT_AIA_TYPE_NONE) { + acpi_dsdt_add_plic_aplic(scope, socket_count, memmap[VIRT_PLIC].base, + memmap[VIRT_PLIC].size, "RSCV0001"); + } else { + acpi_dsdt_add_plic_aplic(scope, socket_count, memmap[VIRT_APLIC_S].base, + memmap[VIRT_APLIC_S].size, "RSCV0002"); + } + acpi_dsdt_add_uart(scope, &memmap[VIRT_UART0], UART0_IRQ); if (socket_count == 1) { diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c index 3d5fe0994d..49cff2a0cb 100644 --- a/hw/scsi/vhost-scsi.c +++ b/hw/scsi/vhost-scsi.c @@ -38,6 +38,7 @@ static const int kernel_feature_bits[] = { VIRTIO_RING_F_EVENT_IDX, VIRTIO_SCSI_F_HOTPLUG, VIRTIO_F_RING_RESET, + VIRTIO_F_IN_ORDER, VIRTIO_F_NOTIFICATION_DATA, VHOST_INVALID_FEATURE_BIT }; diff --git a/hw/scsi/vhost-user-scsi.c b/hw/scsi/vhost-user-scsi.c index cc91ade525..55e4be5b34 100644 --- a/hw/scsi/vhost-user-scsi.c +++ b/hw/scsi/vhost-user-scsi.c @@ -36,6 +36,7 @@ static const int user_feature_bits[] = { VIRTIO_RING_F_EVENT_IDX, VIRTIO_SCSI_F_HOTPLUG, VIRTIO_F_RING_RESET, + VIRTIO_F_IN_ORDER, VIRTIO_F_NOTIFICATION_DATA, VHOST_INVALID_FEATURE_BIT }; diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c index 3b7703489d..a394514264 100644 --- a/hw/smbios/smbios.c +++ b/hw/smbios/smbios.c @@ -1093,6 +1093,7 @@ static bool smbios_get_tables_ep(MachineState *ms, Error **errp) { unsigned i, dimm_cnt, offset; + MachineClass *mc = MACHINE_GET_CLASS(ms); ERRP_GUARD(); assert(ep_type == SMBIOS_ENTRY_POINT_TYPE_32 || @@ -1123,12 +1124,12 @@ static bool smbios_get_tables_ep(MachineState *ms, smbios_build_type_9_table(errp); smbios_build_type_11_table(); -#define MAX_DIMM_SZ (16 * GiB) -#define GET_DIMM_SZ ((i < dimm_cnt - 1) ? MAX_DIMM_SZ \ - : ((current_machine->ram_size - 1) % MAX_DIMM_SZ) + 1) +#define GET_DIMM_SZ ((i < dimm_cnt - 1) ? mc->smbios_memory_device_size \ + : ((current_machine->ram_size - 1) % mc->smbios_memory_device_size) + 1) - dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, MAX_DIMM_SZ) / - MAX_DIMM_SZ; + dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, + mc->smbios_memory_device_size) / + mc->smbios_memory_device_size; /* * The offset determines if we need to keep additional space between diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 6d15b36e0b..cfc44a4569 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -599,7 +599,7 @@ static void vfio_listener_region_add(MemoryListener *listener, IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr); int iommu_idx; - trace_vfio_listener_region_add_iommu(iova, end); + trace_vfio_listener_region_add_iommu(section->mr->name, iova, end); /* * FIXME: For VFIO iommu types which have KVM acceleration to * avoid bouncing all map/unmaps through qemu this way, this @@ -725,6 +725,7 @@ static void vfio_listener_region_del(MemoryListener *listener, if (memory_region_is_iommu(section->mr)) { VFIOGuestIOMMU *giommu; + trace_vfio_listener_region_del_iommu(section->mr->name); QLIST_FOREACH(giommu, &bcontainer->giommu_list, giommu_next) { if (MEMORY_REGION(giommu->iommu_mr) == section->mr && giommu->n.start == section->offset_within_region) { diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index e16179b507..98bd4dccea 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -95,7 +95,8 @@ vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t d vfio_iommu_map_notify(const char *op, uint64_t iova_start, uint64_t iova_end) "iommu %s @ 0x%"PRIx64" - 0x%"PRIx64 vfio_listener_region_skip(const char *name, uint64_t start, uint64_t end) "SKIPPING %s 0x%"PRIx64" - 0x%"PRIx64 vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d" -vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64 +vfio_listener_region_add_iommu(const char* name, uint64_t start, uint64_t end) "region_add [iommu] %s 0x%"PRIx64" - 0x%"PRIx64 +vfio_listener_region_del_iommu(const char *name) "region_del [iommu] %s" vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]" vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index b7c04f0856..04e36ae047 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -116,6 +116,7 @@ virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, u virtio_iommu_set_config(uint8_t bypass) "bypass=0x%x" virtio_iommu_attach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d" virtio_iommu_detach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d" +virtio_iommu_detach_endpoint_from_domain(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d" virtio_iommu_map(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end, uint64_t phys_start, uint32_t flags) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64 " phys_start=0x%"PRIx64" flags=%d" virtio_iommu_unmap(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64 virtio_iommu_unmap_done(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64 diff --git a/hw/virtio/vhost-user-fs.c b/hw/virtio/vhost-user-fs.c index ae48cc1c96..32ee7f496d 100644 --- a/hw/virtio/vhost-user-fs.c +++ b/hw/virtio/vhost-user-fs.c @@ -33,6 +33,7 @@ static const int user_feature_bits[] = { VIRTIO_F_RING_PACKED, VIRTIO_F_IOMMU_PLATFORM, VIRTIO_F_RING_RESET, + VIRTIO_F_IN_ORDER, VIRTIO_F_NOTIFICATION_DATA, VHOST_INVALID_FEATURE_BIT }; diff --git a/hw/virtio/vhost-user-vsock.c b/hw/virtio/vhost-user-vsock.c index 802b44a07d..da3b0e0229 100644 --- a/hw/virtio/vhost-user-vsock.c +++ b/hw/virtio/vhost-user-vsock.c @@ -21,6 +21,7 @@ static const int user_feature_bits[] = { VIRTIO_RING_F_INDIRECT_DESC, VIRTIO_RING_F_EVENT_IDX, VIRTIO_F_NOTIFY_ON_EMPTY, + VIRTIO_F_IN_ORDER, VIRTIO_F_NOTIFICATION_DATA, VHOST_INVALID_FEATURE_BIT }; diff --git a/hw/virtio/virtio-crypto.c b/hw/virtio/virtio-crypto.c index bbe8aa4b99..5034768bff 100644 --- a/hw/virtio/virtio-crypto.c +++ b/hw/virtio/virtio-crypto.c @@ -205,6 +205,7 @@ virtio_crypto_create_asym_session(VirtIOCrypto *vcrypto, int queue_index; uint32_t algo, keytype, keylen; + sreq->info.op_code = opcode; algo = ldl_le_p(&sess_req->para.algo); keytype = ldl_le_p(&sess_req->para.keytype); keylen = ldl_le_p(&sess_req->para.keylen); @@ -224,7 +225,6 @@ virtio_crypto_create_asym_session(VirtIOCrypto *vcrypto, iov_discard_front(&iov, &out_num, keylen); } - sreq->info.op_code = opcode; asym_info = &sreq->info.u.asym_sess_info; asym_info->algo = algo; asym_info->keytype = keytype; diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c index 33ae61c4a6..59ef4fb217 100644 --- a/hw/virtio/virtio-iommu.c +++ b/hw/virtio/virtio-iommu.c @@ -308,6 +308,7 @@ static void virtio_iommu_detach_endpoint_from_domain(VirtIOIOMMUEndpoint *ep) if (!ep->domain) { return; } + trace_virtio_iommu_detach_endpoint_from_domain(domain->id, ep->id); g_tree_foreach(domain->mappings, virtio_iommu_notify_unmap_cb, ep->iommu_mr); QLIST_REMOVE(ep, next); @@ -467,26 +468,6 @@ static AddressSpace *virtio_iommu_find_add_as(PCIBus *bus, void *opaque, return &sdev->as; } -static void virtio_iommu_device_clear(VirtIOIOMMU *s, PCIBus *bus, int devfn) -{ - IOMMUPciBus *sbus = g_hash_table_lookup(s->as_by_busptr, bus); - IOMMUDevice *sdev; - - if (!sbus) { - return; - } - - sdev = sbus->pbdev[devfn]; - if (!sdev) { - return; - } - - g_list_free_full(sdev->resv_regions, g_free); - sdev->resv_regions = NULL; - g_free(sdev); - sbus->pbdev[devfn] = NULL; -} - static gboolean hiod_equal(gconstpointer v1, gconstpointer v2) { const struct hiod_key *key1 = v1; @@ -558,8 +539,6 @@ static int virtio_iommu_set_host_iova_ranges(VirtIOIOMMU *s, PCIBus *bus, { IOMMUPciBus *sbus = g_hash_table_lookup(s->as_by_busptr, bus); IOMMUDevice *sdev; - GList *current_ranges; - GList *l, *tmp, *new_ranges = NULL; int ret = -EINVAL; if (!sbus) { @@ -573,35 +552,10 @@ static int virtio_iommu_set_host_iova_ranges(VirtIOIOMMU *s, PCIBus *bus, return ret; } - current_ranges = sdev->host_resv_ranges; - - g_assert(!sdev->probe_done); - - /* check that each new resv region is included in an existing one */ if (sdev->host_resv_ranges) { - range_inverse_array(iova_ranges, - &new_ranges, - 0, UINT64_MAX); - - for (tmp = new_ranges; tmp; tmp = tmp->next) { - Range *newr = (Range *)tmp->data; - bool included = false; - - for (l = current_ranges; l; l = l->next) { - Range * r = (Range *)l->data; - - if (range_contains_range(r, newr)) { - included = true; - break; - } - } - if (!included) { - goto error; - } - } - /* all new reserved ranges are included in existing ones */ - ret = 0; - goto out; + error_setg(errp, "%s virtio-iommu does not support aliased BDF", + __func__); + return ret; } range_inverse_array(iova_ranges, @@ -610,14 +564,31 @@ static int virtio_iommu_set_host_iova_ranges(VirtIOIOMMU *s, PCIBus *bus, rebuild_resv_regions(sdev); return 0; -error: - error_setg(errp, "%s Conflicting host reserved ranges set!", - __func__); -out: - g_list_free_full(new_ranges, g_free); - return ret; } +static void virtio_iommu_unset_host_iova_ranges(VirtIOIOMMU *s, PCIBus *bus, + int devfn) +{ + IOMMUPciBus *sbus = g_hash_table_lookup(s->as_by_busptr, bus); + IOMMUDevice *sdev; + + if (!sbus) { + return; + } + + sdev = sbus->pbdev[devfn]; + if (!sdev) { + return; + } + + g_list_free_full(g_steal_pointer(&sdev->host_resv_ranges), g_free); + g_list_free_full(sdev->resv_regions, g_free); + sdev->host_resv_ranges = NULL; + sdev->resv_regions = NULL; + add_prop_resv_regions(sdev); +} + + static bool check_page_size_mask(VirtIOIOMMU *viommu, uint64_t new_mask, Error **errp) { @@ -726,9 +697,10 @@ virtio_iommu_unset_iommu_device(PCIBus *bus, void *opaque, int devfn) if (!hiod) { return; } + virtio_iommu_unset_host_iova_ranges(viommu, hiod->aliased_bus, + hiod->aliased_devfn); g_hash_table_remove(viommu->host_iommu_devices, &key); - virtio_iommu_device_clear(viommu, bus, devfn); } static const PCIIOMMUOps virtio_iommu_ops = { @@ -815,6 +787,7 @@ static int virtio_iommu_detach(VirtIOIOMMU *s, if (QLIST_EMPTY(&domain->endpoint_list)) { g_tree_remove(s->domains, GUINT_TO_POINTER(domain->id)); } + g_tree_remove(s->endpoints, GUINT_TO_POINTER(ep_id)); return VIRTIO_IOMMU_S_OK; } @@ -977,7 +950,6 @@ static int virtio_iommu_probe(VirtIOIOMMU *s, } buf += count; free -= count; - sdev->probe_done = true; return VIRTIO_IOMMU_S_OK; } diff --git a/hw/virtio/virtio-net-pci.c b/hw/virtio/virtio-net-pci.c index e03543a70a..dba4987d6e 100644 --- a/hw/virtio/virtio-net-pci.c +++ b/hw/virtio/virtio-net-pci.c @@ -75,6 +75,7 @@ static void virtio_net_pci_class_init(ObjectClass *klass, void *data) k->device_id = PCI_DEVICE_ID_VIRTIO_NET; k->revision = VIRTIO_PCI_ABI_VERSION; k->class_id = PCI_CLASS_NETWORK_ETHERNET; + k->sriov_vf_user_creatable = true; set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); device_class_set_props(dc, virtio_net_properties); vpciklass->realize = virtio_net_pci_realize; diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 9534730bba..0c8fcc5627 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -1955,6 +1955,7 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp) uint8_t *config; uint32_t size; VirtIODevice *vdev = virtio_bus_get_device(bus); + int16_t res; /* * Virtio capabilities present without @@ -2100,6 +2101,14 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp) pci_register_bar(&proxy->pci_dev, proxy->legacy_io_bar_idx, PCI_BASE_ADDRESS_SPACE_IO, &proxy->bar); } + + res = pcie_sriov_pf_init_from_user_created_vfs(&proxy->pci_dev, + proxy->last_pcie_cap_offset, + errp); + if (res > 0) { + proxy->last_pcie_cap_offset += res; + virtio_add_feature(&vdev->host_features, VIRTIO_F_SR_IOV); + } } static void virtio_pci_device_unplugged(DeviceState *d) @@ -2187,7 +2196,7 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) if (pcie_port && pci_is_express(pci_dev)) { int pos; - uint16_t last_pcie_cap_offset = PCI_CONFIG_SPACE_SIZE; + proxy->last_pcie_cap_offset = PCI_CONFIG_SPACE_SIZE; pos = pcie_endpoint_cap_init(pci_dev, 0); assert(pos > 0); @@ -2207,9 +2216,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) pci_set_word(pci_dev->config + pos + PCI_PM_PMC, 0x3); if (proxy->flags & VIRTIO_PCI_FLAG_AER) { - pcie_aer_init(pci_dev, PCI_ERR_VER, last_pcie_cap_offset, + pcie_aer_init(pci_dev, PCI_ERR_VER, proxy->last_pcie_cap_offset, PCI_ERR_SIZEOF, NULL); - last_pcie_cap_offset += PCI_ERR_SIZEOF; + proxy->last_pcie_cap_offset += PCI_ERR_SIZEOF; } if (proxy->flags & VIRTIO_PCI_FLAG_INIT_DEVERR) { @@ -2234,9 +2243,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) } if (proxy->flags & VIRTIO_PCI_FLAG_ATS) { - pcie_ats_init(pci_dev, last_pcie_cap_offset, + pcie_ats_init(pci_dev, proxy->last_pcie_cap_offset, proxy->flags & VIRTIO_PCI_FLAG_ATS_PAGE_ALIGNED); - last_pcie_cap_offset += PCI_EXT_CAP_ATS_SIZEOF; + proxy->last_pcie_cap_offset += PCI_EXT_CAP_ATS_SIZEOF; } if (proxy->flags & VIRTIO_PCI_FLAG_INIT_FLR) { @@ -2263,6 +2272,7 @@ static void virtio_pci_exit(PCIDevice *pci_dev) bool pcie_port = pci_bus_is_express(pci_get_bus(pci_dev)) && !pci_bus_is_root(pci_get_bus(pci_dev)); + pcie_sriov_pf_exit(&proxy->pci_dev); msix_uninit_exclusive_bar(pci_dev); if (proxy->flags & VIRTIO_PCI_FLAG_AER && pcie_port && pci_is_express(pci_dev)) { diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 583a224163..397c261c3c 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -872,6 +872,46 @@ static void virtqueue_packed_fill(VirtQueue *vq, const VirtQueueElement *elem, vq->used_elems[idx].ndescs = elem->ndescs; } +static void virtqueue_ordered_fill(VirtQueue *vq, const VirtQueueElement *elem, + unsigned int len) +{ + unsigned int i, steps, max_steps; + + i = vq->used_idx % vq->vring.num; + steps = 0; + /* + * We shouldn't need to increase 'i' by more than the distance + * between used_idx and last_avail_idx. + */ + max_steps = (vq->last_avail_idx - vq->used_idx) % vq->vring.num; + + /* Search for element in vq->used_elems */ + while (steps <= max_steps) { + /* Found element, set length and mark as filled */ + if (vq->used_elems[i].index == elem->index) { + vq->used_elems[i].len = len; + vq->used_elems[i].in_order_filled = true; + break; + } + + i += vq->used_elems[i].ndescs; + steps += vq->used_elems[i].ndescs; + + if (i >= vq->vring.num) { + i -= vq->vring.num; + } + } + + /* + * We should be able to find a matching VirtQueueElement in + * used_elems. If we don't, this is an error. + */ + if (steps >= max_steps) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: %s cannot fill buffer id %u\n", + __func__, vq->vdev->name, elem->index); + } +} + static void virtqueue_packed_fill_desc(VirtQueue *vq, const VirtQueueElement *elem, unsigned int idx, @@ -922,7 +962,9 @@ void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem, return; } - if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) { + if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_IN_ORDER)) { + virtqueue_ordered_fill(vq, elem, len); + } else if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) { virtqueue_packed_fill(vq, elem, len, idx); } else { virtqueue_split_fill(vq, elem, len, idx); @@ -981,6 +1023,73 @@ static void virtqueue_packed_flush(VirtQueue *vq, unsigned int count) } } +static void virtqueue_ordered_flush(VirtQueue *vq) +{ + unsigned int i = vq->used_idx % vq->vring.num; + unsigned int ndescs = 0; + uint16_t old = vq->used_idx; + uint16_t new; + bool packed; + VRingUsedElem uelem; + + packed = virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED); + + if (packed) { + if (unlikely(!vq->vring.desc)) { + return; + } + } else if (unlikely(!vq->vring.used)) { + return; + } + + /* First expected in-order element isn't ready, nothing to do */ + if (!vq->used_elems[i].in_order_filled) { + return; + } + + /* Search for filled elements in-order */ + while (vq->used_elems[i].in_order_filled) { + /* + * First entry for packed VQs is written last so the guest + * doesn't see invalid descriptors. + */ + if (packed && i != vq->used_idx) { + virtqueue_packed_fill_desc(vq, &vq->used_elems[i], ndescs, false); + } else if (!packed) { + uelem.id = vq->used_elems[i].index; + uelem.len = vq->used_elems[i].len; + vring_used_write(vq, &uelem, i); + } + + vq->used_elems[i].in_order_filled = false; + ndescs += vq->used_elems[i].ndescs; + i += vq->used_elems[i].ndescs; + if (i >= vq->vring.num) { + i -= vq->vring.num; + } + } + + if (packed) { + virtqueue_packed_fill_desc(vq, &vq->used_elems[vq->used_idx], 0, true); + vq->used_idx += ndescs; + if (vq->used_idx >= vq->vring.num) { + vq->used_idx -= vq->vring.num; + vq->used_wrap_counter ^= 1; + vq->signalled_used_valid = false; + } + } else { + /* Make sure buffer is written before we update index. */ + smp_wmb(); + new = old + ndescs; + vring_used_idx_set(vq, new); + if (unlikely((int16_t)(new - vq->signalled_used) < + (uint16_t)(new - old))) { + vq->signalled_used_valid = false; + } + } + vq->inuse -= ndescs; +} + void virtqueue_flush(VirtQueue *vq, unsigned int count) { if (virtio_device_disabled(vq->vdev)) { @@ -988,7 +1097,9 @@ void virtqueue_flush(VirtQueue *vq, unsigned int count) return; } - if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) { + if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_IN_ORDER)) { + virtqueue_ordered_flush(vq); + } else if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) { virtqueue_packed_flush(vq, count); } else { virtqueue_split_flush(vq, count); @@ -1505,7 +1616,7 @@ static void *virtqueue_alloc_element(size_t sz, unsigned out_num, unsigned in_nu static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) { - unsigned int i, head, max; + unsigned int i, head, max, idx; VRingMemoryRegionCaches *caches; MemoryRegionCache indirect_desc_cache; MemoryRegionCache *desc_cache; @@ -1629,6 +1740,13 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) elem->in_sg[i] = iov[out_num + i]; } + if (virtio_vdev_has_feature(vdev, VIRTIO_F_IN_ORDER)) { + idx = (vq->last_avail_idx - 1) % vq->vring.num; + vq->used_elems[idx].index = elem->index; + vq->used_elems[idx].len = elem->len; + vq->used_elems[idx].ndescs = elem->ndescs; + } + vq->inuse++; trace_virtqueue_pop(vq, elem, elem->in_num, elem->out_num); @@ -1762,6 +1880,13 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz) elem->index = id; elem->ndescs = (desc_cache == &indirect_desc_cache) ? 1 : elem_entries; + + if (virtio_vdev_has_feature(vdev, VIRTIO_F_IN_ORDER)) { + vq->used_elems[vq->last_avail_idx].index = elem->index; + vq->used_elems[vq->last_avail_idx].len = elem->len; + vq->used_elems[vq->last_avail_idx].ndescs = elem->ndescs; + } + vq->last_avail_idx += elem->ndescs; vq->inuse += elem->ndescs; diff --git a/include/block/nvme.h b/include/block/nvme.h index 7c77d38174..5298bc4a28 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -799,6 +799,8 @@ typedef struct QEMU_PACKED NvmeDsmRange { enum { NVME_COPY_FORMAT_0 = 0x0, NVME_COPY_FORMAT_1 = 0x1, + NVME_COPY_FORMAT_2 = 0x2, + NVME_COPY_FORMAT_3 = 0x3, }; typedef struct QEMU_PACKED NvmeCopyCmd { @@ -820,25 +822,30 @@ typedef struct QEMU_PACKED NvmeCopyCmd { uint16_t appmask; } NvmeCopyCmd; -typedef struct QEMU_PACKED NvmeCopySourceRangeFormat0 { - uint8_t rsvd0[8]; +typedef struct QEMU_PACKED NvmeCopySourceRangeFormat0_2 { + uint32_t sparams; + uint8_t rsvd4[4]; uint64_t slba; uint16_t nlb; - uint8_t rsvd18[6]; + uint8_t rsvd18[4]; + uint16_t sopt; uint32_t reftag; uint16_t apptag; uint16_t appmask; -} NvmeCopySourceRangeFormat0; +} NvmeCopySourceRangeFormat0_2; -typedef struct QEMU_PACKED NvmeCopySourceRangeFormat1 { - uint8_t rsvd0[8]; +typedef struct QEMU_PACKED NvmeCopySourceRangeFormat1_3 { + uint32_t sparams; + uint8_t rsvd4[4]; uint64_t slba; uint16_t nlb; - uint8_t rsvd18[8]; + uint8_t rsvd18[4]; + uint16_t sopt; + uint8_t rsvd24[2]; uint8_t sr[10]; uint16_t apptag; uint16_t appmask; -} NvmeCopySourceRangeFormat1; +} NvmeCopySourceRangeFormat1_3; enum NvmeAsyncEventRequest { NVME_AER_TYPE_ERROR = 0, @@ -937,6 +944,8 @@ enum NvmeStatusCodes { NVME_INVALID_PROT_INFO = 0x0181, NVME_WRITE_TO_RO = 0x0182, NVME_CMD_SIZE_LIMIT = 0x0183, + NVME_CMD_INCOMP_NS_OR_FMT = 0x0185, + NVME_CMD_OVERLAP_IO_RANGE = 0x0187, NVME_INVALID_ZONE_OP = 0x01b6, NVME_NOZRWA = 0x01b7, NVME_ZONE_BOUNDARY_ERROR = 0x01b8, @@ -1195,11 +1204,15 @@ enum NvmeIdCtrlOncs { NVME_ONCS_TIMESTAMP = 1 << 6, NVME_ONCS_VERIFY = 1 << 7, NVME_ONCS_COPY = 1 << 8, + NVME_ONCS_NVMCSA = 1 << 9, + NVME_ONCS_NVMAFC = 1 << 10, }; enum NvmeIdCtrlOcfs { NVME_OCFS_COPY_FORMAT_0 = 1 << NVME_COPY_FORMAT_0, NVME_OCFS_COPY_FORMAT_1 = 1 << NVME_COPY_FORMAT_1, + NVME_OCFS_COPY_FORMAT_2 = 1 << NVME_COPY_FORMAT_2, + NVME_OCFS_COPY_FORMAT_3 = 1 << NVME_COPY_FORMAT_3, }; enum NvmeIdctrlVwc { @@ -1333,7 +1346,9 @@ typedef struct NvmeHostBehaviorSupport { uint8_t acre; uint8_t etdas; uint8_t lbafee; - uint8_t rsvd3[509]; + uint8_t rsvd3; + uint16_t cdfe; + uint8_t rsvd6[506]; } NvmeHostBehaviorSupport; typedef struct QEMU_PACKED NvmeLBAF { @@ -1833,8 +1848,8 @@ static inline void _nvme_check_size(void) QEMU_BUILD_BUG_ON(sizeof(NvmeZonedResult) != 8); QEMU_BUILD_BUG_ON(sizeof(NvmeCqe) != 16); QEMU_BUILD_BUG_ON(sizeof(NvmeDsmRange) != 16); - QEMU_BUILD_BUG_ON(sizeof(NvmeCopySourceRangeFormat0) != 32); - QEMU_BUILD_BUG_ON(sizeof(NvmeCopySourceRangeFormat1) != 40); + QEMU_BUILD_BUG_ON(sizeof(NvmeCopySourceRangeFormat0_2) != 32); + QEMU_BUILD_BUG_ON(sizeof(NvmeCopySourceRangeFormat1_3) != 40); QEMU_BUILD_BUG_ON(sizeof(NvmeCmd) != 64); QEMU_BUILD_BUG_ON(sizeof(NvmeDeleteQ) != 64); QEMU_BUILD_BUG_ON(sizeof(NvmeCreateCq) != 64); diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 815342d043..240ee04369 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -129,6 +129,14 @@ size_t qemu_ram_pagesize_largest(void); */ void cpu_address_space_init(CPUState *cpu, int asidx, const char *prefix, MemoryRegion *mr); +/** + * cpu_address_space_destroy: + * @cpu: CPU for which address space needs to be destroyed + * @asidx: integer index of this address space + * + * Note that with KVM only one address space is supported. + */ +void cpu_address_space_destroy(CPUState *cpu, int asidx); void cpu_physical_memory_rw(hwaddr addr, void *buf, hwaddr len, bool is_write); diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index 71009f84f5..dac12bd8eb 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -379,4 +379,38 @@ void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, MMUAccessType access_type, int mmu_idx); #endif +/* + * For user-only, helpers that use guest to host address translation + * must protect the actual host memory access by recording 'retaddr' + * for the signal handler. This is required for a race condition in + * which another thread unmaps the page between a probe and the + * actual access. + */ +#ifdef CONFIG_USER_ONLY +extern __thread uintptr_t helper_retaddr; + +static inline void set_helper_retaddr(uintptr_t ra) +{ + helper_retaddr = ra; + /* + * Ensure that this write is visible to the SIGSEGV handler that + * may be invoked due to a subsequent invalid memory operation. + */ + signal_barrier(); +} + +static inline void clear_helper_retaddr(void) +{ + /* + * Ensure that previous memory operations have succeeded before + * removing the data visible to the signal handler. + */ + signal_barrier(); + helper_retaddr = 0; +} +#else +#define set_helper_retaddr(ra) do { } while (0) +#define clear_helper_retaddr() do { } while (0) +#endif + #endif /* CPU_LDST_H */ diff --git a/include/exec/gdbstub.h b/include/exec/gdbstub.h index 1bd2c4ec2a..d73f424f56 100644 --- a/include/exec/gdbstub.h +++ b/include/exec/gdbstub.h @@ -41,6 +41,12 @@ void gdb_register_coprocessor(CPUState *cpu, const GDBFeature *feature, int g_pos); /** + * gdb_unregister_coprocessor_all() - unregisters supplemental set of registers + * @cpu - the CPU associated with registers + */ +void gdb_unregister_coprocessor_all(CPUState *cpu); + +/** * gdbserver_start: start the gdb server * @port_or_device: connection spec for gdb * diff --git a/include/gdbstub/commands.h b/include/gdbstub/commands.h index f3058f9dda..40f0514fe9 100644 --- a/include/gdbstub/commands.h +++ b/include/gdbstub/commands.h @@ -74,23 +74,28 @@ int gdb_put_packet(const char *buf); /** * gdb_extend_query_table() - Extend query table. - * @table: The table with the additional query packet handlers. - * @size: The number of handlers to be added. + * @table: GPtrArray of GdbCmdParseEntry entries. + * + * The caller should free @table afterwards */ -void gdb_extend_query_table(GdbCmdParseEntry *table, int size); +void gdb_extend_query_table(GPtrArray *table); /** * gdb_extend_set_table() - Extend set table. - * @table: The table with the additional set packet handlers. - * @size: The number of handlers to be added. + * @table: GPtrArray of GdbCmdParseEntry entries. + * + * The caller should free @table afterwards */ -void gdb_extend_set_table(GdbCmdParseEntry *table, int size); +void gdb_extend_set_table(GPtrArray *table); /** * gdb_extend_qsupported_features() - Extend the qSupported features string. * @qsupported_features: The additional qSupported feature(s) string. The string * should start with a semicolon and, if there are more than one feature, the - * features should be separate by a semiocolon. + * features should be separate by a semicolon. + * + * The caller should free @qsupported_features afterwards if + * dynamically allocated. */ void gdb_extend_qsupported_features(char *qsupported_features); diff --git a/include/hw/acpi/cpu.h b/include/hw/acpi/cpu.h index e6e1a9ef59..32654dc274 100644 --- a/include/hw/acpi/cpu.h +++ b/include/hw/acpi/cpu.h @@ -19,6 +19,8 @@ #include "hw/boards.h" #include "hw/hotplug.h" +#define ACPI_CPU_HOTPLUG_REG_LEN 12 + typedef struct AcpiCpuStatus { CPUState *cpu; uint64_t arch_id; @@ -61,9 +63,10 @@ typedef void (*build_madt_cpu_fn)(int uid, const CPUArchIdList *apic_ids, GArray *entry, bool force_enabled); void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, - build_madt_cpu_fn build_madt_cpu, hwaddr io_base, + build_madt_cpu_fn build_madt_cpu, hwaddr base_addr, const char *res_root, - const char *event_handler_method); + const char *event_handler_method, + AmlRegionSpace rs); void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list); diff --git a/include/hw/acpi/generic_event_device.h b/include/hw/acpi/generic_event_device.h index ba84ce0214..40af3550b5 100644 --- a/include/hw/acpi/generic_event_device.h +++ b/include/hw/acpi/generic_event_device.h @@ -62,6 +62,7 @@ #include "hw/sysbus.h" #include "hw/acpi/memory_hotplug.h" #include "hw/acpi/ghes.h" +#include "hw/acpi/cpu.h" #include "qom/object.h" #define ACPI_POWER_BUTTON_DEVICE "PWRB" @@ -86,6 +87,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED) #define GED_DEVICE "GED" #define AML_GED_EVT_REG "EREG" #define AML_GED_EVT_SEL "ESEL" +#define AML_GED_EVT_CPU_SCAN_METHOD "\\_SB.GED.CSCN" /* * Platforms need to specify the GED event bitmap @@ -95,6 +97,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED) #define ACPI_GED_MEM_HOTPLUG_EVT 0x1 #define ACPI_GED_PWR_DOWN_EVT 0x2 #define ACPI_GED_NVDIMM_HOTPLUG_EVT 0x4 +#define ACPI_GED_CPU_HOTPLUG_EVT 0x8 typedef struct GEDState { MemoryRegion evt; @@ -106,6 +109,8 @@ struct AcpiGedState { SysBusDevice parent_obj; MemHotplugState memhp_state; MemoryRegion container_memhp; + CPUHotplugState cpuhp_state; + MemoryRegion container_cpuhp; GEDState ged_state; uint32_t ged_event_bitmap; qemu_irq irq; diff --git a/include/hw/boards.h b/include/hw/boards.h index ef6f18f2c1..48ff6d8b93 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -237,6 +237,9 @@ typedef struct { * purposes only. * Applies only to default memory backend, i.e., explicit memory backend * wasn't used. + * @smbios_memory_device_size: + * Default size of memory device, + * SMBIOS 3.1.0 "7.18 Memory Device (Type 17)" */ struct MachineClass { /*< private >*/ @@ -304,6 +307,7 @@ struct MachineClass { const CPUArchIdList *(*possible_cpu_arch_ids)(MachineState *machine); int64_t (*get_default_cpu_node_id)(const MachineState *ms, int idx); ram_addr_t (*fixup_ram_size)(ram_addr_t size); + uint64_t smbios_memory_device_size; }; /** diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index d946161717..1c9c775df6 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -496,6 +496,7 @@ struct CPUState { QSIMPLEQ_HEAD(, qemu_work_item) work_list; struct CPUAddressSpace *cpu_ases; + int cpu_ases_count; int num_ases; AddressSpace *as; MemoryRegion *memory; diff --git a/include/hw/cxl/cxl_device.h b/include/hw/cxl/cxl_device.h index 0a4fcb2800..fdd0f4e62b 100644 --- a/include/hw/cxl/cxl_device.h +++ b/include/hw/cxl/cxl_device.h @@ -181,6 +181,21 @@ typedef struct CXLCCI { uint64_t runtime; QEMUTimer *timer; } bg; + + /* firmware update */ + struct { + uint8_t active_slot; + uint8_t staged_slot; + bool slot[4]; + uint8_t curr_action; + uint8_t curr_slot; + /* handle partial transfers */ + bool transferring; + size_t prev_offset; + size_t prev_len; + time_t last_partxfer; + } fw; + size_t payload_max; /* Pointer to device hosting the CCI */ DeviceState *d; @@ -397,9 +412,14 @@ static inline void __toggle_media(CXLDeviceState *cxl_dstate, int val) #define cxl_dev_enable_media(cxlds) \ do { __toggle_media((cxlds), 0x1); } while (0) -static inline bool sanitize_running(CXLCCI *cci) +static inline bool cxl_dev_media_disabled(CXLDeviceState *cxl_dstate) +{ + uint64_t dev_status_reg = cxl_dstate->mbox_reg_state64[R_CXL_MEM_DEV_STS]; + return FIELD_EX64(dev_status_reg, CXL_MEM_DEV_STS, MEDIA_STATUS) == 0x3; +} +static inline bool scan_media_running(CXLCCI *cci) { - return !!cci->bg.runtime && cci->bg.opcode == 0x4400; + return !!cci->bg.runtime && cci->bg.opcode == 0x4304; } typedef struct CXLError { @@ -422,6 +442,47 @@ typedef struct CXLPoison { typedef QLIST_HEAD(, CXLPoison) CXLPoisonList; #define CXL_POISON_LIST_LIMIT 256 +/* CXL memory device patrol scrub control attributes */ +typedef struct CXLMemPatrolScrubReadAttrs { + uint8_t scrub_cycle_cap; + uint16_t scrub_cycle; + uint8_t scrub_flags; +} QEMU_PACKED CXLMemPatrolScrubReadAttrs; + +typedef struct CXLMemPatrolScrubWriteAttrs { + uint8_t scrub_cycle_hr; + uint8_t scrub_flags; +} QEMU_PACKED CXLMemPatrolScrubWriteAttrs; + +#define CXL_MEMDEV_PS_GET_FEATURE_VERSION 0x01 +#define CXL_MEMDEV_PS_SET_FEATURE_VERSION 0x01 +#define CXL_MEMDEV_PS_SCRUB_CYCLE_CHANGE_CAP_DEFAULT BIT(0) +#define CXL_MEMDEV_PS_SCRUB_REALTIME_REPORT_CAP_DEFAULT BIT(1) +#define CXL_MEMDEV_PS_CUR_SCRUB_CYCLE_DEFAULT 12 +#define CXL_MEMDEV_PS_MIN_SCRUB_CYCLE_DEFAULT 1 +#define CXL_MEMDEV_PS_ENABLE_DEFAULT 0 + +/* CXL memory device DDR5 ECS control attributes */ +typedef struct CXLMemECSReadAttrs { + uint8_t ecs_log_cap; + uint8_t ecs_cap; + uint16_t ecs_config; + uint8_t ecs_flags; +} QEMU_PACKED CXLMemECSReadAttrs; + +typedef struct CXLMemECSWriteAttrs { + uint8_t ecs_log_cap; + uint16_t ecs_config; +} QEMU_PACKED CXLMemECSWriteAttrs; + +#define CXL_ECS_GET_FEATURE_VERSION 0x01 +#define CXL_ECS_SET_FEATURE_VERSION 0x01 +#define CXL_ECS_LOG_ENTRY_TYPE_DEFAULT 0x01 +#define CXL_ECS_REALTIME_REPORT_CAP_DEFAULT 1 +#define CXL_ECS_THRESHOLD_COUNT_DEFAULT 3 /* 3: 256, 4: 1024, 5: 4096 */ +#define CXL_ECS_MODE_DEFAULT 0 +#define CXL_ECS_NUM_MEDIA_FRUS 3 /* Default */ + #define DCD_MAX_NUM_REGION 8 typedef struct CXLDCExtentRaw { @@ -459,6 +520,14 @@ typedef struct CXLDCRegion { unsigned long *blk_bitmap; } CXLDCRegion; +typedef struct CXLSetFeatureInfo { + QemuUUID uuid; + uint8_t data_transfer_flag; + bool data_saved_across_reset; + uint16_t data_offset; + size_t data_size; +} CXLSetFeatureInfo; + struct CXLType3Dev { /* Private */ PCIDevice parent_obj; @@ -491,6 +560,19 @@ struct CXLType3Dev { unsigned int poison_list_cnt; bool poison_list_overflowed; uint64_t poison_list_overflow_ts; + /* Poison Injection - backup */ + CXLPoisonList poison_list_bkp; + CXLPoisonList scan_media_results; + bool scan_media_hasrun; + + CXLSetFeatureInfo set_feat_info; + + /* Patrol scrub control attributes */ + CXLMemPatrolScrubReadAttrs patrol_scrub_attrs; + CXLMemPatrolScrubWriteAttrs patrol_scrub_wr_attrs; + /* ECS control attributes */ + CXLMemECSReadAttrs ecs_attrs[CXL_ECS_NUM_MEDIA_FRUS]; + CXLMemECSWriteAttrs ecs_wr_attrs[CXL_ECS_NUM_MEDIA_FRUS]; struct dynamic_capacity { HostMemoryBackend *host_dc; @@ -554,10 +636,12 @@ CXLRetCode cxl_event_get_records(CXLDeviceState *cxlds, CXLGetEventPayload *pl, size_t *len); CXLRetCode cxl_event_clear_records(CXLDeviceState *cxlds, CXLClearEventPayload *pl); +void cxl_discard_all_event_records(CXLDeviceState *cxlds); void cxl_event_irq_assert(CXLType3Dev *ct3d); void cxl_set_poison_list_overflowed(CXLType3Dev *ct3d); +void cxl_clear_poison_list_overflowed(CXLType3Dev *ct3d); CXLDCRegion *cxl_find_dc_region(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len); diff --git a/include/hw/cxl/cxl_mailbox.h b/include/hw/cxl/cxl_mailbox.h new file mode 100644 index 0000000000..beb048052e --- /dev/null +++ b/include/hw/cxl/cxl_mailbox.h @@ -0,0 +1,18 @@ +/* + * QEMU CXL Mailbox + * + * This work is licensed under the terms of the GNU GPL, version 2. See the + * COPYING file in the top-level directory. + */ + +#ifndef CXL_MAILBOX_H +#define CXL_MAILBOX_H + +#define CXL_MBOX_IMMEDIATE_CONFIG_CHANGE (1 << 1) +#define CXL_MBOX_IMMEDIATE_DATA_CHANGE (1 << 2) +#define CXL_MBOX_IMMEDIATE_POLICY_CHANGE (1 << 3) +#define CXL_MBOX_IMMEDIATE_LOG_CHANGE (1 << 4) +#define CXL_MBOX_SECURITY_STATE_CHANGE (1 << 5) +#define CXL_MBOX_BACKGROUND_OPERATION (1 << 6) + +#endif diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h index ca15132508..e7e41cb939 100644 --- a/include/hw/pci/pci_device.h +++ b/include/hw/pci/pci_device.h @@ -3,6 +3,7 @@ #include "hw/pci/pci.h" #include "hw/pci/pcie.h" +#include "hw/pci/pcie_doe.h" #define TYPE_PCI_DEVICE "pci-device" typedef struct PCIDeviceClass PCIDeviceClass; @@ -37,6 +38,8 @@ struct PCIDeviceClass { uint16_t subsystem_id; /* only for header type = 0 */ const char *romfile; /* rom bar */ + + bool sriov_vf_user_creatable; }; enum PCIReqIDType { @@ -157,9 +160,17 @@ struct PCIDevice { MSIVectorReleaseNotifier msix_vector_release_notifier; MSIVectorPollNotifier msix_vector_poll_notifier; + /* SPDM */ + uint16_t spdm_port; + + /* DOE */ + DOECap doe_spdm; + /* ID of standby device in net_failover pair */ char *failover_pair_id; uint32_t acpi_index; + + char *sriov_pf; }; static inline int pci_intx(PCIDevice *pci_dev) @@ -192,7 +203,7 @@ static inline int pci_is_express_downstream_port(const PCIDevice *d) static inline int pci_is_vf(const PCIDevice *d) { - return d->exp.sriov_vf.pf != NULL; + return d->sriov_pf || d->exp.sriov_vf.pf != NULL; } static inline uint32_t pci_config_size(const PCIDevice *d) diff --git a/include/hw/pci/pcie_doe.h b/include/hw/pci/pcie_doe.h index 87dc17dcef..9e1275db8a 100644 --- a/include/hw/pci/pcie_doe.h +++ b/include/hw/pci/pcie_doe.h @@ -46,6 +46,8 @@ REG32(PCI_DOE_CAP_STATUS, 0) /* PCI-SIG defined Data Object Types - r6.0 Table 6-32 */ #define PCI_SIG_DOE_DISCOVERY 0x00 +#define PCI_SIG_DOE_CMA 0x01 +#define PCI_SIG_DOE_SECURED_CMA 0x02 #define PCI_DOE_DW_SIZE_MAX (1 << 18) #define PCI_DOE_PROTOCOL_NUM_MAX 256 @@ -106,6 +108,9 @@ struct DOECap { /* Protocols and its callback response */ DOEProtocol *protocols; uint16_t protocol_num; + + /* Used for spdm-socket */ + int spdm_socket; }; void pcie_doe_init(PCIDevice *pdev, DOECap *doe_cap, uint16_t offset, diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h index c5d2d318d3..f75b8f22ee 100644 --- a/include/hw/pci/pcie_sriov.h +++ b/include/hw/pci/pcie_sriov.h @@ -18,6 +18,7 @@ typedef struct PCIESriovPF { uint8_t vf_bar_type[PCI_NUM_REGIONS]; /* Store type for each VF bar */ PCIDevice **vf; /* Pointer to an array of num_vfs VF devices */ + bool vf_user_created; /* If VFs are created by user */ } PCIESriovPF; typedef struct PCIESriovVF { @@ -40,6 +41,23 @@ void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num, MemoryRegion *memory); +/** + * pcie_sriov_pf_init_from_user_created_vfs() - Initialize PF with user-created + * VFs. + * @dev: A PCIe device being realized. + * @offset: The offset of the SR-IOV capability. + * @errp: pointer to Error*, to store an error if it happens. + * + * Return: The size of added capability. 0 if the user did not create VFs. + * -1 if failed. + */ +int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev, + uint16_t offset, + Error **errp); + +bool pcie_sriov_register_device(PCIDevice *dev, Error **errp); +void pcie_sriov_unregister_device(PCIDevice *dev); + /* * Default (minimal) page size support values * as required by the SR/IOV standard: diff --git a/include/hw/virtio/virtio-iommu.h b/include/hw/virtio/virtio-iommu.h index bdb3da72d0..7db4210b16 100644 --- a/include/hw/virtio/virtio-iommu.h +++ b/include/hw/virtio/virtio-iommu.h @@ -43,7 +43,6 @@ typedef struct IOMMUDevice { MemoryRegion bypass_mr; /* The alias of shared memory MR */ GList *resv_regions; GList *host_resv_ranges; - bool probe_done; } IOMMUDevice; typedef struct IOMMUPciBus { diff --git a/include/hw/virtio/virtio-pci.h b/include/hw/virtio/virtio-pci.h index 9e67ba38c7..34539f2f67 100644 --- a/include/hw/virtio/virtio-pci.h +++ b/include/hw/virtio/virtio-pci.h @@ -152,6 +152,7 @@ struct VirtIOPCIProxy { uint32_t modern_io_bar_idx; uint32_t modern_mem_bar_idx; int config_cap; + uint16_t last_pcie_cap_offset; uint32_t flags; bool disable_modern; bool ignore_backend_features; diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h index 7512afbc84..d2a1938757 100644 --- a/include/hw/virtio/virtio.h +++ b/include/hw/virtio/virtio.h @@ -69,6 +69,8 @@ typedef struct VirtQueueElement unsigned int ndescs; unsigned int out_num; unsigned int in_num; + /* Element has been processed (VIRTIO_F_IN_ORDER) */ + bool in_order_filled; hwaddr *in_addr; hwaddr *out_addr; struct iovec *in_sg; @@ -371,7 +373,9 @@ typedef struct VirtIORNGConf VirtIORNGConf; DEFINE_PROP_BIT64("packed", _state, _field, \ VIRTIO_F_RING_PACKED, false), \ DEFINE_PROP_BIT64("queue_reset", _state, _field, \ - VIRTIO_F_RING_RESET, true) + VIRTIO_F_RING_RESET, true), \ + DEFINE_PROP_BIT64("in_order", _state, _field, \ + VIRTIO_F_IN_ORDER, false) hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n); bool virtio_queue_enabled_legacy(VirtIODevice *vdev, int n); diff --git a/include/semihosting/syscalls.h b/include/semihosting/syscalls.h index 3a5ec229eb..b5937c619a 100644 --- a/include/semihosting/syscalls.h +++ b/include/semihosting/syscalls.h @@ -9,6 +9,8 @@ #ifndef SEMIHOSTING_SYSCALLS_H #define SEMIHOSTING_SYSCALLS_H +#include "gdbstub/syscalls.h" + /* * Argument loading from the guest is performed by the caller; * results are returned via the 'complete' callback. diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index c31d9c7356..c4a914b3d8 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -313,6 +313,31 @@ int kvm_create_device(KVMState *s, uint64_t type, bool test); */ bool kvm_device_supported(int vmfd, uint64_t type); +/** + * kvm_create_vcpu - Gets a parked KVM vCPU or creates a KVM vCPU + * @cpu: QOM CPUState object for which KVM vCPU has to be fetched/created. + * + * @returns: 0 when success, errno (<0) when failed. + */ +int kvm_create_vcpu(CPUState *cpu); + +/** + * kvm_park_vcpu - Park QEMU KVM vCPU context + * @cpu: QOM CPUState object for which QEMU KVM vCPU context has to be parked. + * + * @returns: none + */ +void kvm_park_vcpu(CPUState *cpu); + +/** + * kvm_unpark_vcpu - unpark QEMU KVM vCPU context + * @s: KVM State + * @vcpu_id: Architecture vCPU ID of the parked vCPU + * + * @returns: KVM fd + */ +int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id); + /* Arch specific hooks */ extern const KVMCapabilityInfo kvm_arch_required_capabilities[]; diff --git a/include/sysemu/spdm-socket.h b/include/sysemu/spdm-socket.h new file mode 100644 index 0000000000..5d8bd9aa4e --- /dev/null +++ b/include/sysemu/spdm-socket.h @@ -0,0 +1,74 @@ +/* + * QEMU SPDM socket support + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef SPDM_REQUESTER_H +#define SPDM_REQUESTER_H + +/** + * spdm_socket_connect: connect to an external SPDM socket + * @port: port to connect to + * @errp: error object handle + * + * This will connect to an external SPDM socket server. On error + * it will return -1 and errp will be set. On success this function + * will return the socket number. + */ +int spdm_socket_connect(uint16_t port, Error **errp); + +/** + * spdm_socket_rsp: send and receive a message to a SPDM server + * @socket: socket returned from spdm_socket_connect() + * @transport_type: SPDM_SOCKET_TRANSPORT_TYPE_* macro + * @req: request buffer + * @req_len: request buffer length + * @rsp: response buffer + * @rsp_len: response buffer length + * + * Send platform data to a SPDM server on socket and then receive + * a response. + */ +uint32_t spdm_socket_rsp(const int socket, uint32_t transport_type, + void *req, uint32_t req_len, + void *rsp, uint32_t rsp_len); + +/** + * spdm_socket_close: send a shutdown command to the server + * @socket: socket returned from spdm_socket_connect() + * @transport_type: SPDM_SOCKET_TRANSPORT_TYPE_* macro + * + * This will issue a shutdown command to the server. + */ +void spdm_socket_close(const int socket, uint32_t transport_type); + +#define SPDM_SOCKET_COMMAND_NORMAL 0x0001 +#define SPDM_SOCKET_COMMAND_OOB_ENCAP_KEY_UPDATE 0x8001 +#define SPDM_SOCKET_COMMAND_CONTINUE 0xFFFD +#define SPDM_SOCKET_COMMAND_SHUTDOWN 0xFFFE +#define SPDM_SOCKET_COMMAND_UNKOWN 0xFFFF +#define SPDM_SOCKET_COMMAND_TEST 0xDEAD + +#define SPDM_SOCKET_TRANSPORT_TYPE_MCTP 0x01 +#define SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE 0x02 + +#define SPDM_SOCKET_MAX_MESSAGE_BUFFER_SIZE 0x1200 + +#endif diff --git a/meson.build b/meson.build index 9d3e2d2ddb..af9f0380e2 100644 --- a/meson.build +++ b/meson.build @@ -2187,6 +2187,19 @@ have_virtfs_proxy_helper = get_option('virtfs_proxy_helper') \ .require(libcap_ng.found(), error_message: 'the virtfs proxy helper requires libcap-ng') \ .allowed() +qga_fsfreeze = false +qga_fstrim = false +if host_os == 'linux' + if cc.has_header_symbol('linux/fs.h', 'FIFREEZE') + qga_fsfreeze = true + endif + if cc.has_header_symbol('linux/fs.h', 'FITRIM') + qga_fstrim = true + endif +elif host_os == 'freebsd' and cc.has_header_symbol('ufs/ffs/fs.h', 'UFSSUSPEND') + qga_fsfreeze = true +endif + if get_option('block_drv_ro_whitelist') == '' config_host_data.set('CONFIG_BDRV_RO_WHITELIST', '') else @@ -2263,6 +2276,7 @@ config_host_data.set('CONFIG_ATTR', libattr.found()) config_host_data.set('CONFIG_BDRV_WHITELIST_TOOLS', get_option('block_drv_whitelist_in_tools')) config_host_data.set('CONFIG_BRLAPI', brlapi.found()) config_host_data.set('CONFIG_BSD', host_os in bsd_oses) +config_host_data.set('CONFIG_FREEBSD', host_os == 'freebsd') config_host_data.set('CONFIG_CAPSTONE', capstone.found()) config_host_data.set('CONFIG_COCOA', cocoa.found()) config_host_data.set('CONFIG_DARWIN', host_os == 'darwin') @@ -2423,6 +2437,8 @@ config_host_data.set('CONFIG_DEBUG_TCG', get_option('debug_tcg')) config_host_data.set('CONFIG_DEBUG_REMAP', get_option('debug_remap')) config_host_data.set('CONFIG_QOM_CAST_DEBUG', get_option('qom_cast_debug')) config_host_data.set('CONFIG_REPLICATION', get_option('replication').allowed()) +config_host_data.set('CONFIG_FSFREEZE', qga_fsfreeze) +config_host_data.set('CONFIG_FSTRIM', qga_fstrim) # has_header config_host_data.set('CONFIG_EPOLL', cc.has_header('sys/epoll.h')) diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index daa38428c5..03457ead66 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -62,6 +62,7 @@ const int vdpa_feature_bits[] = { VIRTIO_F_RING_PACKED, VIRTIO_F_RING_RESET, VIRTIO_F_VERSION_1, + VIRTIO_F_IN_ORDER, VIRTIO_F_NOTIFICATION_DATA, VIRTIO_NET_F_CSUM, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, diff --git a/qapi/machine-target.json b/qapi/machine-target.json index 7edb876b5c..a552e2b0ce 100644 --- a/qapi/machine-target.json +++ b/qapi/machine-target.json @@ -21,8 +21,9 @@ # @props: a dictionary of QOM properties to be applied # # @deprecated-props: a list of properties that are flagged as deprecated -# by the CPU vendor. These props are a subset of the full model's -# definition list of properties. (since 9.1) +# by the CPU vendor. These properties are either a subset of the +# properties enabled on the CPU model, or a set of properties +# deprecated across all models for the architecture. # # Since: 2.8 ## diff --git a/qga/commands-bsd.c b/qga/commands-bsd.c index 17bddda1cf..9ce48af311 100644 --- a/qga/commands-bsd.c +++ b/qga/commands-bsd.c @@ -149,30 +149,6 @@ int qmp_guest_fsfreeze_do_thaw(Error **errp) } return ret; } - -GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestDiskInfoList *qmp_guest_get_disks(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestDiskStatsInfoList *qmp_guest_get_diskstats(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestCpuStatsList *qmp_guest_get_cpustats(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} #endif /* CONFIG_FSFREEZE */ #ifdef HAVE_GETIFADDRS diff --git a/qga/commands-common.h b/qga/commands-common.h index 8c1c56aac9..263e7c0525 100644 --- a/qga/commands-common.h +++ b/qga/commands-common.h @@ -15,19 +15,10 @@ #if defined(__linux__) #include <linux/fs.h> -#ifdef FIFREEZE -#define CONFIG_FSFREEZE -#endif -#ifdef FITRIM -#define CONFIG_FSTRIM -#endif #endif /* __linux__ */ #ifdef __FreeBSD__ #include <ufs/ffs/fs.h> -#ifdef UFSSUSPEND -#define CONFIG_FSFREEZE -#endif #endif /* __FreeBSD__ */ #if defined(CONFIG_FSFREEZE) || defined(CONFIG_FSTRIM) diff --git a/qga/commands-linux.c b/qga/commands-linux.c index 214e408fcd..51d5e3d927 100644 --- a/qga/commands-linux.c +++ b/qga/commands-linux.c @@ -13,10 +13,26 @@ #include "qemu/osdep.h" #include "qapi/error.h" +#include "qga-qapi-commands.h" +#include "qapi/error.h" +#include "qapi/qmp/qerror.h" #include "commands-common.h" #include "cutils.h" #include <mntent.h> #include <sys/ioctl.h> +#include <mntent.h> +#include <linux/nvme_ioctl.h> +#include "block/nvme.h" + +#ifdef CONFIG_LIBUDEV +#include <libudev.h> +#endif + +#ifdef HAVE_GETIFADDRS +#include <net/if.h> +#endif + +#include <sys/statvfs.h> #if defined(CONFIG_FSFREEZE) || defined(CONFIG_FSTRIM) static int dev_major_minor(const char *devpath, @@ -284,3 +300,1925 @@ int qmp_guest_fsfreeze_do_thaw(Error **errp) return i; } #endif /* CONFIG_FSFREEZE */ + +#if defined(CONFIG_FSFREEZE) + +static char *get_pci_driver(char const *syspath, int pathlen, Error **errp) +{ + char *path; + char *dpath; + char *driver = NULL; + char buf[PATH_MAX]; + ssize_t len; + + path = g_strndup(syspath, pathlen); + dpath = g_strdup_printf("%s/driver", path); + len = readlink(dpath, buf, sizeof(buf) - 1); + if (len != -1) { + buf[len] = 0; + driver = g_path_get_basename(buf); + } + g_free(dpath); + g_free(path); + return driver; +} + +static int compare_uint(const void *_a, const void *_b) +{ + unsigned int a = *(unsigned int *)_a; + unsigned int b = *(unsigned int *)_b; + + return a < b ? -1 : a > b ? 1 : 0; +} + +/* Walk the specified sysfs and build a sorted list of host or ata numbers */ +static int build_hosts(char const *syspath, char const *host, bool ata, + unsigned int *hosts, int hosts_max, Error **errp) +{ + char *path; + DIR *dir; + struct dirent *entry; + int i = 0; + + path = g_strndup(syspath, host - syspath); + dir = opendir(path); + if (!dir) { + error_setg_errno(errp, errno, "opendir(\"%s\")", path); + g_free(path); + return -1; + } + + while (i < hosts_max) { + entry = readdir(dir); + if (!entry) { + break; + } + if (ata && sscanf(entry->d_name, "ata%d", hosts + i) == 1) { + ++i; + } else if (!ata && sscanf(entry->d_name, "host%d", hosts + i) == 1) { + ++i; + } + } + + qsort(hosts, i, sizeof(hosts[0]), compare_uint); + + g_free(path); + closedir(dir); + return i; +} + +/* + * Store disk device info for devices on the PCI bus. + * Returns true if information has been stored, or false for failure. + */ +static bool build_guest_fsinfo_for_pci_dev(char const *syspath, + GuestDiskAddress *disk, + Error **errp) +{ + unsigned int pci[4], host, hosts[8], tgt[3]; + int i, nhosts = 0, pcilen; + GuestPCIAddress *pciaddr = disk->pci_controller; + bool has_ata = false, has_host = false, has_tgt = false; + char *p, *q, *driver = NULL; + bool ret = false; + + p = strstr(syspath, "/devices/pci"); + if (!p || sscanf(p + 12, "%*x:%*x/%x:%x:%x.%x%n", + pci, pci + 1, pci + 2, pci + 3, &pcilen) < 4) { + g_debug("only pci device is supported: sysfs path '%s'", syspath); + return false; + } + + p += 12 + pcilen; + while (true) { + driver = get_pci_driver(syspath, p - syspath, errp); + if (driver && (g_str_equal(driver, "ata_piix") || + g_str_equal(driver, "sym53c8xx") || + g_str_equal(driver, "virtio-pci") || + g_str_equal(driver, "ahci") || + g_str_equal(driver, "nvme") || + g_str_equal(driver, "xhci_hcd") || + g_str_equal(driver, "ehci-pci"))) { + break; + } + + g_free(driver); + if (sscanf(p, "/%x:%x:%x.%x%n", + pci, pci + 1, pci + 2, pci + 3, &pcilen) == 4) { + p += pcilen; + continue; + } + + g_debug("unsupported driver or sysfs path '%s'", syspath); + return false; + } + + p = strstr(syspath, "/target"); + if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u", + tgt, tgt + 1, tgt + 2) == 3) { + has_tgt = true; + } + + p = strstr(syspath, "/ata"); + if (p) { + q = p + 4; + has_ata = true; + } else { + p = strstr(syspath, "/host"); + q = p + 5; + } + if (p && sscanf(q, "%u", &host) == 1) { + has_host = true; + nhosts = build_hosts(syspath, p, has_ata, hosts, + ARRAY_SIZE(hosts), errp); + if (nhosts < 0) { + goto cleanup; + } + } + + pciaddr->domain = pci[0]; + pciaddr->bus = pci[1]; + pciaddr->slot = pci[2]; + pciaddr->function = pci[3]; + + if (strcmp(driver, "ata_piix") == 0) { + /* a host per ide bus, target*:0:<unit>:0 */ + if (!has_host || !has_tgt) { + g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver); + goto cleanup; + } + for (i = 0; i < nhosts; i++) { + if (host == hosts[i]) { + disk->bus_type = GUEST_DISK_BUS_TYPE_IDE; + disk->bus = i; + disk->unit = tgt[1]; + break; + } + } + if (i >= nhosts) { + g_debug("no host for '%s' (driver '%s')", syspath, driver); + goto cleanup; + } + } else if (strcmp(driver, "sym53c8xx") == 0) { + /* scsi(LSI Logic): target*:0:<unit>:0 */ + if (!has_tgt) { + g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver); + goto cleanup; + } + disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI; + disk->unit = tgt[1]; + } else if (strcmp(driver, "virtio-pci") == 0) { + if (has_tgt) { + /* virtio-scsi: target*:0:0:<unit> */ + disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI; + disk->unit = tgt[2]; + } else { + /* virtio-blk: 1 disk per 1 device */ + disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO; + } + } else if (strcmp(driver, "ahci") == 0) { + /* ahci: 1 host per 1 unit */ + if (!has_host || !has_tgt) { + g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver); + goto cleanup; + } + for (i = 0; i < nhosts; i++) { + if (host == hosts[i]) { + disk->unit = i; + disk->bus_type = GUEST_DISK_BUS_TYPE_SATA; + break; + } + } + if (i >= nhosts) { + g_debug("no host for '%s' (driver '%s')", syspath, driver); + goto cleanup; + } + } else if (strcmp(driver, "nvme") == 0) { + disk->bus_type = GUEST_DISK_BUS_TYPE_NVME; + } else if (strcmp(driver, "ehci-pci") == 0 || strcmp(driver, "xhci_hcd") == 0) { + disk->bus_type = GUEST_DISK_BUS_TYPE_USB; + } else { + g_debug("unknown driver '%s' (sysfs path '%s')", driver, syspath); + goto cleanup; + } + + ret = true; + +cleanup: + g_free(driver); + return ret; +} + +/* + * Store disk device info for non-PCI virtio devices (for example s390x + * channel I/O devices). Returns true if information has been stored, or + * false for failure. + */ +static bool build_guest_fsinfo_for_nonpci_virtio(char const *syspath, + GuestDiskAddress *disk, + Error **errp) +{ + unsigned int tgt[3]; + char *p; + + if (!strstr(syspath, "/virtio") || !strstr(syspath, "/block")) { + g_debug("Unsupported virtio device '%s'", syspath); + return false; + } + + p = strstr(syspath, "/target"); + if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u", + &tgt[0], &tgt[1], &tgt[2]) == 3) { + /* virtio-scsi: target*:0:<target>:<unit> */ + disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI; + disk->bus = tgt[0]; + disk->target = tgt[1]; + disk->unit = tgt[2]; + } else { + /* virtio-blk: 1 disk per 1 device */ + disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO; + } + + return true; +} + +/* + * Store disk device info for CCW devices (s390x channel I/O devices). + * Returns true if information has been stored, or false for failure. + */ +static bool build_guest_fsinfo_for_ccw_dev(char const *syspath, + GuestDiskAddress *disk, + Error **errp) +{ + unsigned int cssid, ssid, subchno, devno; + char *p; + + p = strstr(syspath, "/devices/css"); + if (!p || sscanf(p + 12, "%*x/%x.%x.%x/%*x.%*x.%x/", + &cssid, &ssid, &subchno, &devno) < 4) { + g_debug("could not parse ccw device sysfs path: %s", syspath); + return false; + } + + disk->ccw_address = g_new0(GuestCCWAddress, 1); + disk->ccw_address->cssid = cssid; + disk->ccw_address->ssid = ssid; + disk->ccw_address->subchno = subchno; + disk->ccw_address->devno = devno; + + if (strstr(p, "/virtio")) { + build_guest_fsinfo_for_nonpci_virtio(syspath, disk, errp); + } + + return true; +} + +/* Store disk device info specified by @sysfs into @fs */ +static void build_guest_fsinfo_for_real_device(char const *syspath, + GuestFilesystemInfo *fs, + Error **errp) +{ + GuestDiskAddress *disk; + GuestPCIAddress *pciaddr; + bool has_hwinf; +#ifdef CONFIG_LIBUDEV + struct udev *udev = NULL; + struct udev_device *udevice = NULL; +#endif + + pciaddr = g_new0(GuestPCIAddress, 1); + pciaddr->domain = -1; /* -1 means field is invalid */ + pciaddr->bus = -1; + pciaddr->slot = -1; + pciaddr->function = -1; + + disk = g_new0(GuestDiskAddress, 1); + disk->pci_controller = pciaddr; + disk->bus_type = GUEST_DISK_BUS_TYPE_UNKNOWN; + +#ifdef CONFIG_LIBUDEV + udev = udev_new(); + udevice = udev_device_new_from_syspath(udev, syspath); + if (udev == NULL || udevice == NULL) { + g_debug("failed to query udev"); + } else { + const char *devnode, *serial; + devnode = udev_device_get_devnode(udevice); + if (devnode != NULL) { + disk->dev = g_strdup(devnode); + } + serial = udev_device_get_property_value(udevice, "ID_SERIAL"); + if (serial != NULL && *serial != 0) { + disk->serial = g_strdup(serial); + } + } + + udev_unref(udev); + udev_device_unref(udevice); +#endif + + if (strstr(syspath, "/devices/pci")) { + has_hwinf = build_guest_fsinfo_for_pci_dev(syspath, disk, errp); + } else if (strstr(syspath, "/devices/css")) { + has_hwinf = build_guest_fsinfo_for_ccw_dev(syspath, disk, errp); + } else if (strstr(syspath, "/virtio")) { + has_hwinf = build_guest_fsinfo_for_nonpci_virtio(syspath, disk, errp); + } else { + g_debug("Unsupported device type for '%s'", syspath); + has_hwinf = false; + } + + if (has_hwinf || disk->dev || disk->serial) { + QAPI_LIST_PREPEND(fs->disk, disk); + } else { + qapi_free_GuestDiskAddress(disk); + } +} + +static void build_guest_fsinfo_for_device(char const *devpath, + GuestFilesystemInfo *fs, + Error **errp); + +/* Store a list of slave devices of virtual volume specified by @syspath into + * @fs */ +static void build_guest_fsinfo_for_virtual_device(char const *syspath, + GuestFilesystemInfo *fs, + Error **errp) +{ + Error *err = NULL; + DIR *dir; + char *dirpath; + struct dirent *entry; + + dirpath = g_strdup_printf("%s/slaves", syspath); + dir = opendir(dirpath); + if (!dir) { + if (errno != ENOENT) { + error_setg_errno(errp, errno, "opendir(\"%s\")", dirpath); + } + g_free(dirpath); + return; + } + + for (;;) { + errno = 0; + entry = readdir(dir); + if (entry == NULL) { + if (errno) { + error_setg_errno(errp, errno, "readdir(\"%s\")", dirpath); + } + break; + } + + if (entry->d_type == DT_LNK) { + char *path; + + g_debug(" slave device '%s'", entry->d_name); + path = g_strdup_printf("%s/slaves/%s", syspath, entry->d_name); + build_guest_fsinfo_for_device(path, fs, &err); + g_free(path); + + if (err) { + error_propagate(errp, err); + break; + } + } + } + + g_free(dirpath); + closedir(dir); +} + +static bool is_disk_virtual(const char *devpath, Error **errp) +{ + g_autofree char *syspath = realpath(devpath, NULL); + + if (!syspath) { + error_setg_errno(errp, errno, "realpath(\"%s\")", devpath); + return false; + } + return strstr(syspath, "/devices/virtual/block/") != NULL; +} + +/* Dispatch to functions for virtual/real device */ +static void build_guest_fsinfo_for_device(char const *devpath, + GuestFilesystemInfo *fs, + Error **errp) +{ + ERRP_GUARD(); + g_autofree char *syspath = NULL; + bool is_virtual = false; + + syspath = realpath(devpath, NULL); + if (!syspath) { + if (errno != ENOENT) { + error_setg_errno(errp, errno, "realpath(\"%s\")", devpath); + return; + } + + /* ENOENT: This devpath may not exist because of container config */ + if (!fs->name) { + fs->name = g_path_get_basename(devpath); + } + return; + } + + if (!fs->name) { + fs->name = g_path_get_basename(syspath); + } + + g_debug(" parse sysfs path '%s'", syspath); + is_virtual = is_disk_virtual(syspath, errp); + if (*errp != NULL) { + return; + } + if (is_virtual) { + build_guest_fsinfo_for_virtual_device(syspath, fs, errp); + } else { + build_guest_fsinfo_for_real_device(syspath, fs, errp); + } +} + +#ifdef CONFIG_LIBUDEV + +/* + * Wrapper around build_guest_fsinfo_for_device() for getting just + * the disk address. + */ +static GuestDiskAddress *get_disk_address(const char *syspath, Error **errp) +{ + g_autoptr(GuestFilesystemInfo) fs = NULL; + + fs = g_new0(GuestFilesystemInfo, 1); + build_guest_fsinfo_for_device(syspath, fs, errp); + if (fs->disk != NULL) { + return g_steal_pointer(&fs->disk->value); + } + return NULL; +} + +static char *get_alias_for_syspath(const char *syspath) +{ + struct udev *udev = NULL; + struct udev_device *udevice = NULL; + char *ret = NULL; + + udev = udev_new(); + if (udev == NULL) { + g_debug("failed to query udev"); + goto out; + } + udevice = udev_device_new_from_syspath(udev, syspath); + if (udevice == NULL) { + g_debug("failed to query udev for path: %s", syspath); + goto out; + } else { + const char *alias = udev_device_get_property_value( + udevice, "DM_NAME"); + /* + * NULL means there was an error and empty string means there is no + * alias. In case of no alias we return NULL instead of empty string. + */ + if (alias == NULL) { + g_debug("failed to query udev for device alias for: %s", + syspath); + } else if (*alias != 0) { + ret = g_strdup(alias); + } + } + +out: + udev_unref(udev); + udev_device_unref(udevice); + return ret; +} + +static char *get_device_for_syspath(const char *syspath) +{ + struct udev *udev = NULL; + struct udev_device *udevice = NULL; + char *ret = NULL; + + udev = udev_new(); + if (udev == NULL) { + g_debug("failed to query udev"); + goto out; + } + udevice = udev_device_new_from_syspath(udev, syspath); + if (udevice == NULL) { + g_debug("failed to query udev for path: %s", syspath); + goto out; + } else { + ret = g_strdup(udev_device_get_devnode(udevice)); + } + +out: + udev_unref(udev); + udev_device_unref(udevice); + return ret; +} + +static void get_disk_deps(const char *disk_dir, GuestDiskInfo *disk) +{ + g_autofree char *deps_dir = NULL; + const gchar *dep; + GDir *dp_deps = NULL; + + /* List dependent disks */ + deps_dir = g_strdup_printf("%s/slaves", disk_dir); + g_debug(" listing entries in: %s", deps_dir); + dp_deps = g_dir_open(deps_dir, 0, NULL); + if (dp_deps == NULL) { + g_debug("failed to list entries in %s", deps_dir); + return; + } + disk->has_dependencies = true; + while ((dep = g_dir_read_name(dp_deps)) != NULL) { + g_autofree char *dep_dir = NULL; + char *dev_name; + + /* Add dependent disks */ + dep_dir = g_strdup_printf("%s/%s", deps_dir, dep); + dev_name = get_device_for_syspath(dep_dir); + if (dev_name != NULL) { + g_debug(" adding dependent device: %s", dev_name); + QAPI_LIST_PREPEND(disk->dependencies, dev_name); + } + } + g_dir_close(dp_deps); +} + +/* + * Detect partitions subdirectory, name is "<disk_name><number>" or + * "<disk_name>p<number>" + * + * @disk_name -- last component of /sys path (e.g. sda) + * @disk_dir -- sys path of the disk (e.g. /sys/block/sda) + * @disk_dev -- device node of the disk (e.g. /dev/sda) + */ +static GuestDiskInfoList *get_disk_partitions( + GuestDiskInfoList *list, + const char *disk_name, const char *disk_dir, + const char *disk_dev) +{ + GuestDiskInfoList *ret = list; + struct dirent *de_disk; + DIR *dp_disk = NULL; + size_t len = strlen(disk_name); + + dp_disk = opendir(disk_dir); + while ((de_disk = readdir(dp_disk)) != NULL) { + g_autofree char *partition_dir = NULL; + char *dev_name; + GuestDiskInfo *partition; + + if (!(de_disk->d_type & DT_DIR)) { + continue; + } + + if (!(strncmp(disk_name, de_disk->d_name, len) == 0 && + ((*(de_disk->d_name + len) == 'p' && + isdigit(*(de_disk->d_name + len + 1))) || + isdigit(*(de_disk->d_name + len))))) { + continue; + } + + partition_dir = g_strdup_printf("%s/%s", + disk_dir, de_disk->d_name); + dev_name = get_device_for_syspath(partition_dir); + if (dev_name == NULL) { + g_debug("Failed to get device name for syspath: %s", + disk_dir); + continue; + } + partition = g_new0(GuestDiskInfo, 1); + partition->name = dev_name; + partition->partition = true; + partition->has_dependencies = true; + /* Add parent disk as dependent for easier tracking of hierarchy */ + QAPI_LIST_PREPEND(partition->dependencies, g_strdup(disk_dev)); + + QAPI_LIST_PREPEND(ret, partition); + } + closedir(dp_disk); + + return ret; +} + +static void get_nvme_smart(GuestDiskInfo *disk) +{ + int fd; + GuestNVMeSmart *smart; + NvmeSmartLog log = {0}; + struct nvme_admin_cmd cmd = { + .opcode = NVME_ADM_CMD_GET_LOG_PAGE, + .nsid = NVME_NSID_BROADCAST, + .addr = (uintptr_t)&log, + .data_len = sizeof(log), + .cdw10 = NVME_LOG_SMART_INFO | (1 << 15) /* RAE bit */ + | (((sizeof(log) >> 2) - 1) << 16) + }; + + fd = qga_open_cloexec(disk->name, O_RDONLY, 0); + if (fd == -1) { + g_debug("Failed to open device: %s: %s", disk->name, g_strerror(errno)); + return; + } + + if (ioctl(fd, NVME_IOCTL_ADMIN_CMD, &cmd)) { + g_debug("Failed to get smart: %s: %s", disk->name, g_strerror(errno)); + close(fd); + return; + } + + disk->smart = g_new0(GuestDiskSmart, 1); + disk->smart->type = GUEST_DISK_BUS_TYPE_NVME; + + smart = &disk->smart->u.nvme; + smart->critical_warning = log.critical_warning; + smart->temperature = lduw_le_p(&log.temperature); /* unaligned field */ + smart->available_spare = log.available_spare; + smart->available_spare_threshold = log.available_spare_threshold; + smart->percentage_used = log.percentage_used; + smart->data_units_read_lo = le64_to_cpu(log.data_units_read[0]); + smart->data_units_read_hi = le64_to_cpu(log.data_units_read[1]); + smart->data_units_written_lo = le64_to_cpu(log.data_units_written[0]); + smart->data_units_written_hi = le64_to_cpu(log.data_units_written[1]); + smart->host_read_commands_lo = le64_to_cpu(log.host_read_commands[0]); + smart->host_read_commands_hi = le64_to_cpu(log.host_read_commands[1]); + smart->host_write_commands_lo = le64_to_cpu(log.host_write_commands[0]); + smart->host_write_commands_hi = le64_to_cpu(log.host_write_commands[1]); + smart->controller_busy_time_lo = le64_to_cpu(log.controller_busy_time[0]); + smart->controller_busy_time_hi = le64_to_cpu(log.controller_busy_time[1]); + smart->power_cycles_lo = le64_to_cpu(log.power_cycles[0]); + smart->power_cycles_hi = le64_to_cpu(log.power_cycles[1]); + smart->power_on_hours_lo = le64_to_cpu(log.power_on_hours[0]); + smart->power_on_hours_hi = le64_to_cpu(log.power_on_hours[1]); + smart->unsafe_shutdowns_lo = le64_to_cpu(log.unsafe_shutdowns[0]); + smart->unsafe_shutdowns_hi = le64_to_cpu(log.unsafe_shutdowns[1]); + smart->media_errors_lo = le64_to_cpu(log.media_errors[0]); + smart->media_errors_hi = le64_to_cpu(log.media_errors[1]); + smart->number_of_error_log_entries_lo = + le64_to_cpu(log.number_of_error_log_entries[0]); + smart->number_of_error_log_entries_hi = + le64_to_cpu(log.number_of_error_log_entries[1]); + + close(fd); +} + +static void get_disk_smart(GuestDiskInfo *disk) +{ + if (disk->address + && (disk->address->bus_type == GUEST_DISK_BUS_TYPE_NVME)) { + get_nvme_smart(disk); + } +} + +GuestDiskInfoList *qmp_guest_get_disks(Error **errp) +{ + GuestDiskInfoList *ret = NULL; + GuestDiskInfo *disk; + DIR *dp = NULL; + struct dirent *de = NULL; + + g_debug("listing /sys/block directory"); + dp = opendir("/sys/block"); + if (dp == NULL) { + error_setg_errno(errp, errno, "Can't open directory \"/sys/block\""); + return NULL; + } + while ((de = readdir(dp)) != NULL) { + g_autofree char *disk_dir = NULL, *line = NULL, + *size_path = NULL; + char *dev_name; + Error *local_err = NULL; + if (de->d_type != DT_LNK) { + g_debug(" skipping entry: %s", de->d_name); + continue; + } + + /* Check size and skip zero-sized disks */ + g_debug(" checking disk size"); + size_path = g_strdup_printf("/sys/block/%s/size", de->d_name); + if (!g_file_get_contents(size_path, &line, NULL, NULL)) { + g_debug(" failed to read disk size"); + continue; + } + if (g_strcmp0(line, "0\n") == 0) { + g_debug(" skipping zero-sized disk"); + continue; + } + + g_debug(" adding %s", de->d_name); + disk_dir = g_strdup_printf("/sys/block/%s", de->d_name); + dev_name = get_device_for_syspath(disk_dir); + if (dev_name == NULL) { + g_debug("Failed to get device name for syspath: %s", + disk_dir); + continue; + } + disk = g_new0(GuestDiskInfo, 1); + disk->name = dev_name; + disk->partition = false; + disk->alias = get_alias_for_syspath(disk_dir); + QAPI_LIST_PREPEND(ret, disk); + + /* Get address for non-virtual devices */ + bool is_virtual = is_disk_virtual(disk_dir, &local_err); + if (local_err != NULL) { + g_debug(" failed to check disk path, ignoring error: %s", + error_get_pretty(local_err)); + error_free(local_err); + local_err = NULL; + /* Don't try to get the address */ + is_virtual = true; + } + if (!is_virtual) { + disk->address = get_disk_address(disk_dir, &local_err); + if (local_err != NULL) { + g_debug(" failed to get device info, ignoring error: %s", + error_get_pretty(local_err)); + error_free(local_err); + local_err = NULL; + } + } + + get_disk_deps(disk_dir, disk); + get_disk_smart(disk); + ret = get_disk_partitions(ret, de->d_name, disk_dir, dev_name); + } + + closedir(dp); + + return ret; +} + +#endif + +/* Return a list of the disk device(s)' info which @mount lies on */ +static GuestFilesystemInfo *build_guest_fsinfo(struct FsMount *mount, + Error **errp) +{ + GuestFilesystemInfo *fs = g_malloc0(sizeof(*fs)); + struct statvfs buf; + unsigned long used, nonroot_total, fr_size; + char *devpath = g_strdup_printf("/sys/dev/block/%u:%u", + mount->devmajor, mount->devminor); + + fs->mountpoint = g_strdup(mount->dirname); + fs->type = g_strdup(mount->devtype); + build_guest_fsinfo_for_device(devpath, fs, errp); + + if (statvfs(fs->mountpoint, &buf) == 0) { + fr_size = buf.f_frsize; + used = buf.f_blocks - buf.f_bfree; + nonroot_total = used + buf.f_bavail; + fs->used_bytes = used * fr_size; + fs->total_bytes = nonroot_total * fr_size; + fs->total_bytes_privileged = buf.f_blocks * fr_size; + + fs->has_total_bytes = true; + fs->has_total_bytes_privileged = true; + fs->has_used_bytes = true; + } + + g_free(devpath); + + return fs; +} + +GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp) +{ + FsMountList mounts; + struct FsMount *mount; + GuestFilesystemInfoList *ret = NULL; + Error *local_err = NULL; + + QTAILQ_INIT(&mounts); + if (!build_fs_mount_list(&mounts, &local_err)) { + error_propagate(errp, local_err); + return NULL; + } + + QTAILQ_FOREACH(mount, &mounts, next) { + g_debug("Building guest fsinfo for '%s'", mount->dirname); + + QAPI_LIST_PREPEND(ret, build_guest_fsinfo(mount, &local_err)); + if (local_err) { + error_propagate(errp, local_err); + qapi_free_GuestFilesystemInfoList(ret); + ret = NULL; + break; + } + } + + free_fs_mount_list(&mounts); + return ret; +} +#endif /* CONFIG_FSFREEZE */ + +#if defined(CONFIG_FSTRIM) +/* + * Walk list of mounted file systems in the guest, and trim them. + */ +GuestFilesystemTrimResponse * +qmp_guest_fstrim(bool has_minimum, int64_t minimum, Error **errp) +{ + GuestFilesystemTrimResponse *response; + GuestFilesystemTrimResult *result; + int ret = 0; + FsMountList mounts; + struct FsMount *mount; + int fd; + struct fstrim_range r; + + slog("guest-fstrim called"); + + QTAILQ_INIT(&mounts); + if (!build_fs_mount_list(&mounts, errp)) { + return NULL; + } + + response = g_malloc0(sizeof(*response)); + + QTAILQ_FOREACH(mount, &mounts, next) { + result = g_malloc0(sizeof(*result)); + result->path = g_strdup(mount->dirname); + + QAPI_LIST_PREPEND(response->paths, result); + + fd = qga_open_cloexec(mount->dirname, O_RDONLY, 0); + if (fd == -1) { + result->error = g_strdup_printf("failed to open: %s", + strerror(errno)); + continue; + } + + /* We try to cull filesystems we know won't work in advance, but other + * filesystems may not implement fstrim for less obvious reasons. + * These will report EOPNOTSUPP; while in some other cases ENOTTY + * will be reported (e.g. CD-ROMs). + * Any other error means an unexpected error. + */ + r.start = 0; + r.len = -1; + r.minlen = has_minimum ? minimum : 0; + ret = ioctl(fd, FITRIM, &r); + if (ret == -1) { + if (errno == ENOTTY || errno == EOPNOTSUPP) { + result->error = g_strdup("trim not supported"); + } else { + result->error = g_strdup_printf("failed to trim: %s", + strerror(errno)); + } + close(fd); + continue; + } + + result->has_minimum = true; + result->minimum = r.minlen; + result->has_trimmed = true; + result->trimmed = r.len; + close(fd); + } + + free_fs_mount_list(&mounts); + return response; +} +#endif /* CONFIG_FSTRIM */ + +#define LINUX_SYS_STATE_FILE "/sys/power/state" +#define SUSPEND_SUPPORTED 0 +#define SUSPEND_NOT_SUPPORTED 1 + +typedef enum { + SUSPEND_MODE_DISK = 0, + SUSPEND_MODE_RAM = 1, + SUSPEND_MODE_HYBRID = 2, +} SuspendMode; + +/* + * Executes a command in a child process using g_spawn_sync, + * returning an int >= 0 representing the exit status of the + * process. + * + * If the program wasn't found in path, returns -1. + * + * If a problem happened when creating the child process, + * returns -1 and errp is set. + */ +static int run_process_child(const char *command[], Error **errp) +{ + int exit_status, spawn_flag; + GError *g_err = NULL; + bool success; + + spawn_flag = G_SPAWN_SEARCH_PATH | G_SPAWN_STDOUT_TO_DEV_NULL | + G_SPAWN_STDERR_TO_DEV_NULL; + + success = g_spawn_sync(NULL, (char **)command, NULL, spawn_flag, + NULL, NULL, NULL, NULL, + &exit_status, &g_err); + + if (success) { + return WEXITSTATUS(exit_status); + } + + if (g_err && (g_err->code != G_SPAWN_ERROR_NOENT)) { + error_setg(errp, "failed to create child process, error '%s'", + g_err->message); + } + + g_error_free(g_err); + return -1; +} + +static bool systemd_supports_mode(SuspendMode mode, Error **errp) +{ + const char *systemctl_args[3] = {"systemd-hibernate", "systemd-suspend", + "systemd-hybrid-sleep"}; + const char *cmd[4] = {"systemctl", "status", systemctl_args[mode], NULL}; + int status; + + status = run_process_child(cmd, errp); + + /* + * systemctl status uses LSB return codes so we can expect + * status > 0 and be ok. To assert if the guest has support + * for the selected suspend mode, status should be < 4. 4 is + * the code for unknown service status, the return value when + * the service does not exist. A common value is status = 3 + * (program is not running). + */ + if (status > 0 && status < 4) { + return true; + } + + return false; +} + +static void systemd_suspend(SuspendMode mode, Error **errp) +{ + Error *local_err = NULL; + const char *systemctl_args[3] = {"hibernate", "suspend", "hybrid-sleep"}; + const char *cmd[3] = {"systemctl", systemctl_args[mode], NULL}; + int status; + + status = run_process_child(cmd, &local_err); + + if (status == 0) { + return; + } + + if ((status == -1) && !local_err) { + error_setg(errp, "the helper program 'systemctl %s' was not found", + systemctl_args[mode]); + return; + } + + if (local_err) { + error_propagate(errp, local_err); + } else { + error_setg(errp, "the helper program 'systemctl %s' returned an " + "unexpected exit status code (%d)", + systemctl_args[mode], status); + } +} + +static bool pmutils_supports_mode(SuspendMode mode, Error **errp) +{ + Error *local_err = NULL; + const char *pmutils_args[3] = {"--hibernate", "--suspend", + "--suspend-hybrid"}; + const char *cmd[3] = {"pm-is-supported", pmutils_args[mode], NULL}; + int status; + + status = run_process_child(cmd, &local_err); + + if (status == SUSPEND_SUPPORTED) { + return true; + } + + if ((status == -1) && !local_err) { + return false; + } + + if (local_err) { + error_propagate(errp, local_err); + } else { + error_setg(errp, + "the helper program '%s' returned an unexpected exit" + " status code (%d)", "pm-is-supported", status); + } + + return false; +} + +static void pmutils_suspend(SuspendMode mode, Error **errp) +{ + Error *local_err = NULL; + const char *pmutils_binaries[3] = {"pm-hibernate", "pm-suspend", + "pm-suspend-hybrid"}; + const char *cmd[2] = {pmutils_binaries[mode], NULL}; + int status; + + status = run_process_child(cmd, &local_err); + + if (status == 0) { + return; + } + + if ((status == -1) && !local_err) { + error_setg(errp, "the helper program '%s' was not found", + pmutils_binaries[mode]); + return; + } + + if (local_err) { + error_propagate(errp, local_err); + } else { + error_setg(errp, + "the helper program '%s' returned an unexpected exit" + " status code (%d)", pmutils_binaries[mode], status); + } +} + +static bool linux_sys_state_supports_mode(SuspendMode mode, Error **errp) +{ + const char *sysfile_strs[3] = {"disk", "mem", NULL}; + const char *sysfile_str = sysfile_strs[mode]; + char buf[32]; /* hopefully big enough */ + int fd; + ssize_t ret; + + if (!sysfile_str) { + error_setg(errp, "unknown guest suspend mode"); + return false; + } + + fd = open(LINUX_SYS_STATE_FILE, O_RDONLY); + if (fd < 0) { + return false; + } + + ret = read(fd, buf, sizeof(buf) - 1); + close(fd); + if (ret <= 0) { + return false; + } + buf[ret] = '\0'; + + if (strstr(buf, sysfile_str)) { + return true; + } + return false; +} + +static void linux_sys_state_suspend(SuspendMode mode, Error **errp) +{ + g_autoptr(GError) local_gerr = NULL; + const char *sysfile_strs[3] = {"disk", "mem", NULL}; + const char *sysfile_str = sysfile_strs[mode]; + + if (!sysfile_str) { + error_setg(errp, "unknown guest suspend mode"); + return; + } + + if (!g_file_set_contents(LINUX_SYS_STATE_FILE, sysfile_str, + -1, &local_gerr)) { + error_setg(errp, "suspend: cannot write to '%s': %s", + LINUX_SYS_STATE_FILE, local_gerr->message); + return; + } +} + +static void guest_suspend(SuspendMode mode, Error **errp) +{ + Error *local_err = NULL; + bool mode_supported = false; + + if (systemd_supports_mode(mode, &local_err)) { + mode_supported = true; + systemd_suspend(mode, &local_err); + + if (!local_err) { + return; + } + } + + error_free(local_err); + local_err = NULL; + + if (pmutils_supports_mode(mode, &local_err)) { + mode_supported = true; + pmutils_suspend(mode, &local_err); + + if (!local_err) { + return; + } + } + + error_free(local_err); + local_err = NULL; + + if (linux_sys_state_supports_mode(mode, &local_err)) { + mode_supported = true; + linux_sys_state_suspend(mode, &local_err); + } + + if (!mode_supported) { + error_free(local_err); + error_setg(errp, + "the requested suspend mode is not supported by the guest"); + } else { + error_propagate(errp, local_err); + } +} + +void qmp_guest_suspend_disk(Error **errp) +{ + guest_suspend(SUSPEND_MODE_DISK, errp); +} + +void qmp_guest_suspend_ram(Error **errp) +{ + guest_suspend(SUSPEND_MODE_RAM, errp); +} + +void qmp_guest_suspend_hybrid(Error **errp) +{ + guest_suspend(SUSPEND_MODE_HYBRID, errp); +} + +/* Transfer online/offline status between @vcpu and the guest system. + * + * On input either @errp or *@errp must be NULL. + * + * In system-to-@vcpu direction, the following @vcpu fields are accessed: + * - R: vcpu->logical_id + * - W: vcpu->online + * - W: vcpu->can_offline + * + * In @vcpu-to-system direction, the following @vcpu fields are accessed: + * - R: vcpu->logical_id + * - R: vcpu->online + * + * Written members remain unmodified on error. + */ +static void transfer_vcpu(GuestLogicalProcessor *vcpu, bool sys2vcpu, + char *dirpath, Error **errp) +{ + int fd; + int res; + int dirfd; + static const char fn[] = "online"; + + dirfd = open(dirpath, O_RDONLY | O_DIRECTORY); + if (dirfd == -1) { + error_setg_errno(errp, errno, "open(\"%s\")", dirpath); + return; + } + + fd = openat(dirfd, fn, sys2vcpu ? O_RDONLY : O_RDWR); + if (fd == -1) { + if (errno != ENOENT) { + error_setg_errno(errp, errno, "open(\"%s/%s\")", dirpath, fn); + } else if (sys2vcpu) { + vcpu->online = true; + vcpu->can_offline = false; + } else if (!vcpu->online) { + error_setg(errp, "logical processor #%" PRId64 " can't be " + "offlined", vcpu->logical_id); + } /* otherwise pretend successful re-onlining */ + } else { + unsigned char status; + + res = pread(fd, &status, 1, 0); + if (res == -1) { + error_setg_errno(errp, errno, "pread(\"%s/%s\")", dirpath, fn); + } else if (res == 0) { + error_setg(errp, "pread(\"%s/%s\"): unexpected EOF", dirpath, + fn); + } else if (sys2vcpu) { + vcpu->online = (status != '0'); + vcpu->can_offline = true; + } else if (vcpu->online != (status != '0')) { + status = '0' + vcpu->online; + if (pwrite(fd, &status, 1, 0) == -1) { + error_setg_errno(errp, errno, "pwrite(\"%s/%s\")", dirpath, + fn); + } + } /* otherwise pretend successful re-(on|off)-lining */ + + res = close(fd); + g_assert(res == 0); + } + + res = close(dirfd); + g_assert(res == 0); +} + +GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp) +{ + GuestLogicalProcessorList *head, **tail; + const char *cpu_dir = "/sys/devices/system/cpu"; + const gchar *line; + g_autoptr(GDir) cpu_gdir = NULL; + Error *local_err = NULL; + + head = NULL; + tail = &head; + cpu_gdir = g_dir_open(cpu_dir, 0, NULL); + + if (cpu_gdir == NULL) { + error_setg_errno(errp, errno, "failed to list entries: %s", cpu_dir); + return NULL; + } + + while (local_err == NULL && (line = g_dir_read_name(cpu_gdir)) != NULL) { + GuestLogicalProcessor *vcpu; + int64_t id; + if (sscanf(line, "cpu%" PRId64, &id)) { + g_autofree char *path = g_strdup_printf("/sys/devices/system/cpu/" + "cpu%" PRId64 "/", id); + vcpu = g_malloc0(sizeof *vcpu); + vcpu->logical_id = id; + vcpu->has_can_offline = true; /* lolspeak ftw */ + transfer_vcpu(vcpu, true, path, &local_err); + QAPI_LIST_APPEND(tail, vcpu); + } + } + + if (local_err == NULL) { + /* there's no guest with zero VCPUs */ + g_assert(head != NULL); + return head; + } + + qapi_free_GuestLogicalProcessorList(head); + error_propagate(errp, local_err); + return NULL; +} + +int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp) +{ + int64_t processed; + Error *local_err = NULL; + + processed = 0; + while (vcpus != NULL) { + char *path = g_strdup_printf("/sys/devices/system/cpu/cpu%" PRId64 "/", + vcpus->value->logical_id); + + transfer_vcpu(vcpus->value, false, path, &local_err); + g_free(path); + if (local_err != NULL) { + break; + } + ++processed; + vcpus = vcpus->next; + } + + if (local_err != NULL) { + if (processed == 0) { + error_propagate(errp, local_err); + } else { + error_free(local_err); + } + } + + return processed; +} + + +static void ga_read_sysfs_file(int dirfd, const char *pathname, char *buf, + int size, Error **errp) +{ + int fd; + int res; + + errno = 0; + fd = openat(dirfd, pathname, O_RDONLY); + if (fd == -1) { + error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname); + return; + } + + res = pread(fd, buf, size, 0); + if (res == -1) { + error_setg_errno(errp, errno, "pread sysfs file \"%s\"", pathname); + } else if (res == 0) { + error_setg(errp, "pread sysfs file \"%s\": unexpected EOF", pathname); + } + close(fd); +} + +static void ga_write_sysfs_file(int dirfd, const char *pathname, + const char *buf, int size, Error **errp) +{ + int fd; + + errno = 0; + fd = openat(dirfd, pathname, O_WRONLY); + if (fd == -1) { + error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname); + return; + } + + if (pwrite(fd, buf, size, 0) == -1) { + error_setg_errno(errp, errno, "pwrite sysfs file \"%s\"", pathname); + } + + close(fd); +} + +/* Transfer online/offline status between @mem_blk and the guest system. + * + * On input either @errp or *@errp must be NULL. + * + * In system-to-@mem_blk direction, the following @mem_blk fields are accessed: + * - R: mem_blk->phys_index + * - W: mem_blk->online + * - W: mem_blk->can_offline + * + * In @mem_blk-to-system direction, the following @mem_blk fields are accessed: + * - R: mem_blk->phys_index + * - R: mem_blk->online + *- R: mem_blk->can_offline + * Written members remain unmodified on error. + */ +static void transfer_memory_block(GuestMemoryBlock *mem_blk, bool sys2memblk, + GuestMemoryBlockResponse *result, + Error **errp) +{ + char *dirpath; + int dirfd; + char *status; + Error *local_err = NULL; + + if (!sys2memblk) { + DIR *dp; + + if (!result) { + error_setg(errp, "Internal error, 'result' should not be NULL"); + return; + } + errno = 0; + dp = opendir("/sys/devices/system/memory/"); + /* if there is no 'memory' directory in sysfs, + * we think this VM does not support online/offline memory block, + * any other solution? + */ + if (!dp) { + if (errno == ENOENT) { + result->response = + GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED; + } + goto out1; + } + closedir(dp); + } + + dirpath = g_strdup_printf("/sys/devices/system/memory/memory%" PRId64 "/", + mem_blk->phys_index); + dirfd = open(dirpath, O_RDONLY | O_DIRECTORY); + if (dirfd == -1) { + if (sys2memblk) { + error_setg_errno(errp, errno, "open(\"%s\")", dirpath); + } else { + if (errno == ENOENT) { + result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_NOT_FOUND; + } else { + result->response = + GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED; + } + } + g_free(dirpath); + goto out1; + } + g_free(dirpath); + + status = g_malloc0(10); + ga_read_sysfs_file(dirfd, "state", status, 10, &local_err); + if (local_err) { + /* treat with sysfs file that not exist in old kernel */ + if (errno == ENOENT) { + error_free(local_err); + if (sys2memblk) { + mem_blk->online = true; + mem_blk->can_offline = false; + } else if (!mem_blk->online) { + result->response = + GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED; + } + } else { + if (sys2memblk) { + error_propagate(errp, local_err); + } else { + error_free(local_err); + result->response = + GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED; + } + } + goto out2; + } + + if (sys2memblk) { + char removable = '0'; + + mem_blk->online = (strncmp(status, "online", 6) == 0); + + ga_read_sysfs_file(dirfd, "removable", &removable, 1, &local_err); + if (local_err) { + /* if no 'removable' file, it doesn't support offline mem blk */ + if (errno == ENOENT) { + error_free(local_err); + mem_blk->can_offline = false; + } else { + error_propagate(errp, local_err); + } + } else { + mem_blk->can_offline = (removable != '0'); + } + } else { + if (mem_blk->online != (strncmp(status, "online", 6) == 0)) { + const char *new_state = mem_blk->online ? "online" : "offline"; + + ga_write_sysfs_file(dirfd, "state", new_state, strlen(new_state), + &local_err); + if (local_err) { + error_free(local_err); + result->response = + GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED; + goto out2; + } + + result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_SUCCESS; + result->has_error_code = false; + } /* otherwise pretend successful re-(on|off)-lining */ + } + g_free(status); + close(dirfd); + return; + +out2: + g_free(status); + close(dirfd); +out1: + if (!sys2memblk) { + result->has_error_code = true; + result->error_code = errno; + } +} + +GuestMemoryBlockList *qmp_guest_get_memory_blocks(Error **errp) +{ + GuestMemoryBlockList *head, **tail; + Error *local_err = NULL; + struct dirent *de; + DIR *dp; + + head = NULL; + tail = &head; + + dp = opendir("/sys/devices/system/memory/"); + if (!dp) { + /* it's ok if this happens to be a system that doesn't expose + * memory blocks via sysfs, but otherwise we should report + * an error + */ + if (errno != ENOENT) { + error_setg_errno(errp, errno, "Can't open directory" + "\"/sys/devices/system/memory/\""); + } + return NULL; + } + + /* Note: the phys_index of memory block may be discontinuous, + * this is because a memblk is the unit of the Sparse Memory design, which + * allows discontinuous memory ranges (ex. NUMA), so here we should + * traverse the memory block directory. + */ + while ((de = readdir(dp)) != NULL) { + GuestMemoryBlock *mem_blk; + + if ((strncmp(de->d_name, "memory", 6) != 0) || + !(de->d_type & DT_DIR)) { + continue; + } + + mem_blk = g_malloc0(sizeof *mem_blk); + /* The d_name is "memoryXXX", phys_index is block id, same as XXX */ + mem_blk->phys_index = strtoul(&de->d_name[6], NULL, 10); + mem_blk->has_can_offline = true; /* lolspeak ftw */ + transfer_memory_block(mem_blk, true, NULL, &local_err); + if (local_err) { + break; + } + + QAPI_LIST_APPEND(tail, mem_blk); + } + + closedir(dp); + if (local_err == NULL) { + /* there's no guest with zero memory blocks */ + if (head == NULL) { + error_setg(errp, "guest reported zero memory blocks!"); + } + return head; + } + + qapi_free_GuestMemoryBlockList(head); + error_propagate(errp, local_err); + return NULL; +} + +GuestMemoryBlockResponseList * +qmp_guest_set_memory_blocks(GuestMemoryBlockList *mem_blks, Error **errp) +{ + GuestMemoryBlockResponseList *head, **tail; + Error *local_err = NULL; + + head = NULL; + tail = &head; + + while (mem_blks != NULL) { + GuestMemoryBlockResponse *result; + GuestMemoryBlock *current_mem_blk = mem_blks->value; + + result = g_malloc0(sizeof(*result)); + result->phys_index = current_mem_blk->phys_index; + transfer_memory_block(current_mem_blk, false, result, &local_err); + if (local_err) { /* should never happen */ + goto err; + } + + QAPI_LIST_APPEND(tail, result); + mem_blks = mem_blks->next; + } + + return head; +err: + qapi_free_GuestMemoryBlockResponseList(head); + error_propagate(errp, local_err); + return NULL; +} + +GuestMemoryBlockInfo *qmp_guest_get_memory_block_info(Error **errp) +{ + Error *local_err = NULL; + char *dirpath; + int dirfd; + char *buf; + GuestMemoryBlockInfo *info; + + dirpath = g_strdup_printf("/sys/devices/system/memory/"); + dirfd = open(dirpath, O_RDONLY | O_DIRECTORY); + if (dirfd == -1) { + error_setg_errno(errp, errno, "open(\"%s\")", dirpath); + g_free(dirpath); + return NULL; + } + g_free(dirpath); + + buf = g_malloc0(20); + ga_read_sysfs_file(dirfd, "block_size_bytes", buf, 20, &local_err); + close(dirfd); + if (local_err) { + g_free(buf); + error_propagate(errp, local_err); + return NULL; + } + + info = g_new0(GuestMemoryBlockInfo, 1); + info->size = strtol(buf, NULL, 16); /* the unit is bytes */ + + g_free(buf); + + return info; +} + +#define MAX_NAME_LEN 128 +static GuestDiskStatsInfoList *guest_get_diskstats(Error **errp) +{ + GuestDiskStatsInfoList *head = NULL, **tail = &head; + const char *diskstats = "/proc/diskstats"; + FILE *fp; + size_t n; + char *line = NULL; + + fp = fopen(diskstats, "r"); + if (fp == NULL) { + error_setg_errno(errp, errno, "open(\"%s\")", diskstats); + return NULL; + } + + while (getline(&line, &n, fp) != -1) { + g_autofree GuestDiskStatsInfo *diskstatinfo = NULL; + g_autofree GuestDiskStats *diskstat = NULL; + char dev_name[MAX_NAME_LEN]; + unsigned int ios_pgr, tot_ticks, rq_ticks, wr_ticks, dc_ticks, fl_ticks; + unsigned long rd_ios, rd_merges_or_rd_sec, rd_ticks_or_wr_sec, wr_ios; + unsigned long wr_merges, rd_sec_or_wr_ios, wr_sec; + unsigned long dc_ios, dc_merges, dc_sec, fl_ios; + unsigned int major, minor; + int i; + + i = sscanf(line, "%u %u %s %lu %lu %lu" + "%lu %lu %lu %lu %u %u %u %u" + "%lu %lu %lu %u %lu %u", + &major, &minor, dev_name, + &rd_ios, &rd_merges_or_rd_sec, &rd_sec_or_wr_ios, + &rd_ticks_or_wr_sec, &wr_ios, &wr_merges, &wr_sec, + &wr_ticks, &ios_pgr, &tot_ticks, &rq_ticks, + &dc_ios, &dc_merges, &dc_sec, &dc_ticks, + &fl_ios, &fl_ticks); + + if (i < 7) { + continue; + } + + diskstatinfo = g_new0(GuestDiskStatsInfo, 1); + diskstatinfo->name = g_strdup(dev_name); + diskstatinfo->major = major; + diskstatinfo->minor = minor; + + diskstat = g_new0(GuestDiskStats, 1); + if (i == 7) { + diskstat->has_read_ios = true; + diskstat->read_ios = rd_ios; + diskstat->has_read_sectors = true; + diskstat->read_sectors = rd_merges_or_rd_sec; + diskstat->has_write_ios = true; + diskstat->write_ios = rd_sec_or_wr_ios; + diskstat->has_write_sectors = true; + diskstat->write_sectors = rd_ticks_or_wr_sec; + } + if (i >= 14) { + diskstat->has_read_ios = true; + diskstat->read_ios = rd_ios; + diskstat->has_read_sectors = true; + diskstat->read_sectors = rd_sec_or_wr_ios; + diskstat->has_read_merges = true; + diskstat->read_merges = rd_merges_or_rd_sec; + diskstat->has_read_ticks = true; + diskstat->read_ticks = rd_ticks_or_wr_sec; + diskstat->has_write_ios = true; + diskstat->write_ios = wr_ios; + diskstat->has_write_sectors = true; + diskstat->write_sectors = wr_sec; + diskstat->has_write_merges = true; + diskstat->write_merges = wr_merges; + diskstat->has_write_ticks = true; + diskstat->write_ticks = wr_ticks; + diskstat->has_ios_pgr = true; + diskstat->ios_pgr = ios_pgr; + diskstat->has_total_ticks = true; + diskstat->total_ticks = tot_ticks; + diskstat->has_weight_ticks = true; + diskstat->weight_ticks = rq_ticks; + } + if (i >= 18) { + diskstat->has_discard_ios = true; + diskstat->discard_ios = dc_ios; + diskstat->has_discard_merges = true; + diskstat->discard_merges = dc_merges; + diskstat->has_discard_sectors = true; + diskstat->discard_sectors = dc_sec; + diskstat->has_discard_ticks = true; + diskstat->discard_ticks = dc_ticks; + } + if (i >= 20) { + diskstat->has_flush_ios = true; + diskstat->flush_ios = fl_ios; + diskstat->has_flush_ticks = true; + diskstat->flush_ticks = fl_ticks; + } + + diskstatinfo->stats = g_steal_pointer(&diskstat); + QAPI_LIST_APPEND(tail, diskstatinfo); + diskstatinfo = NULL; + } + free(line); + fclose(fp); + return head; +} + +GuestDiskStatsInfoList *qmp_guest_get_diskstats(Error **errp) +{ + return guest_get_diskstats(errp); +} + +GuestCpuStatsList *qmp_guest_get_cpustats(Error **errp) +{ + GuestCpuStatsList *head = NULL, **tail = &head; + const char *cpustats = "/proc/stat"; + int clk_tck = sysconf(_SC_CLK_TCK); + FILE *fp; + size_t n; + char *line = NULL; + + fp = fopen(cpustats, "r"); + if (fp == NULL) { + error_setg_errno(errp, errno, "open(\"%s\")", cpustats); + return NULL; + } + + while (getline(&line, &n, fp) != -1) { + GuestCpuStats *cpustat = NULL; + GuestLinuxCpuStats *linuxcpustat; + int i; + unsigned long user, system, idle, iowait, irq, softirq, steal, guest; + unsigned long nice, guest_nice; + char name[64]; + + i = sscanf(line, "%s %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu", + name, &user, &nice, &system, &idle, &iowait, &irq, &softirq, + &steal, &guest, &guest_nice); + + /* drop "cpu 1 2 3 ...", get "cpuX 1 2 3 ..." only */ + if ((i == EOF) || strncmp(name, "cpu", 3) || (name[3] == '\0')) { + continue; + } + + if (i < 5) { + slog("Parsing cpu stat from %s failed, see \"man proc\"", cpustats); + break; + } + + cpustat = g_new0(GuestCpuStats, 1); + cpustat->type = GUEST_CPU_STATS_TYPE_LINUX; + + linuxcpustat = &cpustat->u.q_linux; + linuxcpustat->cpu = atoi(&name[3]); + linuxcpustat->user = user * 1000 / clk_tck; + linuxcpustat->nice = nice * 1000 / clk_tck; + linuxcpustat->system = system * 1000 / clk_tck; + linuxcpustat->idle = idle * 1000 / clk_tck; + + if (i > 5) { + linuxcpustat->has_iowait = true; + linuxcpustat->iowait = iowait * 1000 / clk_tck; + } + + if (i > 6) { + linuxcpustat->has_irq = true; + linuxcpustat->irq = irq * 1000 / clk_tck; + linuxcpustat->has_softirq = true; + linuxcpustat->softirq = softirq * 1000 / clk_tck; + } + + if (i > 8) { + linuxcpustat->has_steal = true; + linuxcpustat->steal = steal * 1000 / clk_tck; + } + + if (i > 9) { + linuxcpustat->has_guest = true; + linuxcpustat->guest = guest * 1000 / clk_tck; + } + + if (i > 10) { + linuxcpustat->has_guest = true; + linuxcpustat->guest = guest * 1000 / clk_tck; + linuxcpustat->has_guestnice = true; + linuxcpustat->guestnice = guest_nice * 1000 / clk_tck; + } + + QAPI_LIST_APPEND(tail, cpustat); + } + + free(line); + fclose(fp); + return head; +} + +static char *hexToIPAddress(const void *hexValue, int is_ipv6) +{ + if (is_ipv6) { + char addr[INET6_ADDRSTRLEN]; + struct in6_addr in6; + const char *hexStr = (const char *)hexValue; + int i; + + for (i = 0; i < 16; i++) { + sscanf(&hexStr[i * 2], "%02hhx", &in6.s6_addr[i]); + } + inet_ntop(AF_INET6, &in6, addr, INET6_ADDRSTRLEN); + + return g_strdup(addr); + } else { + unsigned int hexInt = *(unsigned int *)hexValue; + unsigned int byte1 = (hexInt >> 24) & 0xFF; + unsigned int byte2 = (hexInt >> 16) & 0xFF; + unsigned int byte3 = (hexInt >> 8) & 0xFF; + unsigned int byte4 = hexInt & 0xFF; + + return g_strdup_printf("%u.%u.%u.%u", byte4, byte3, byte2, byte1); + } +} + +GuestNetworkRouteList *qmp_guest_network_get_route(Error **errp) +{ + GuestNetworkRouteList *head = NULL, **tail = &head; + const char *routeFiles[] = {"/proc/net/route", "/proc/net/ipv6_route"}; + FILE *fp; + size_t n; + char *line = NULL; + int firstLine; + int is_ipv6; + int i; + + for (i = 0; i < 2; i++) { + firstLine = 1; + is_ipv6 = (i == 1); + fp = fopen(routeFiles[i], "r"); + if (fp == NULL) { + error_setg_errno(errp, errno, "open(\"%s\")", routeFiles[i]); + free(line); + continue; + } + + while (getline(&line, &n, fp) != -1) { + if (firstLine && !is_ipv6) { + firstLine = 0; + continue; + } + GuestNetworkRoute *route = NULL; + GuestNetworkRoute *networkroute; + char Iface[IFNAMSIZ]; + if (is_ipv6) { + char Destination[33], Source[33], NextHop[33]; + int DesPrefixlen, SrcPrefixlen, Metric, RefCnt, Use, Flags; + + /* Parse the line and extract the values */ + if (sscanf(line, "%32s %x %32s %x %32s %x %x %x %x %s", + Destination, &DesPrefixlen, Source, + &SrcPrefixlen, NextHop, &Metric, &RefCnt, + &Use, &Flags, Iface) != 10) { + continue; + } + + route = g_new0(GuestNetworkRoute, 1); + networkroute = route; + networkroute->iface = g_strdup(Iface); + networkroute->destination = hexToIPAddress(Destination, 1); + networkroute->metric = Metric; + networkroute->source = hexToIPAddress(Source, 1); + networkroute->desprefixlen = g_strdup_printf( + "%d", DesPrefixlen + ); + networkroute->srcprefixlen = g_strdup_printf( + "%d", SrcPrefixlen + ); + networkroute->nexthop = hexToIPAddress(NextHop, 1); + networkroute->has_flags = true; + networkroute->flags = Flags; + networkroute->has_refcnt = true; + networkroute->refcnt = RefCnt; + networkroute->has_use = true; + networkroute->use = Use; + networkroute->version = 6; + } else { + unsigned int Destination, Gateway, Mask, Flags; + int RefCnt, Use, Metric, MTU, Window, IRTT; + + /* Parse the line and extract the values */ + if (sscanf(line, "%s %X %X %x %d %d %d %X %d %d %d", + Iface, &Destination, &Gateway, &Flags, &RefCnt, + &Use, &Metric, &Mask, &MTU, &Window, &IRTT) != 11) { + continue; + } + + route = g_new0(GuestNetworkRoute, 1); + networkroute = route; + networkroute->iface = g_strdup(Iface); + networkroute->destination = hexToIPAddress(&Destination, 0); + networkroute->gateway = hexToIPAddress(&Gateway, 0); + networkroute->mask = hexToIPAddress(&Mask, 0); + networkroute->metric = Metric; + networkroute->has_flags = true; + networkroute->flags = Flags; + networkroute->has_refcnt = true; + networkroute->refcnt = RefCnt; + networkroute->has_use = true; + networkroute->use = Use; + networkroute->has_mtu = true; + networkroute->mtu = MTU; + networkroute->has_window = true; + networkroute->window = Window; + networkroute->has_irtt = true; + networkroute->irtt = IRTT; + networkroute->version = 4; + } + + QAPI_LIST_APPEND(tail, route); + } + + free(line); + fclose(fp); + } + + return head; +} diff --git a/qga/commands-posix.c b/qga/commands-posix.c index 7f05996495..c2bd0b4316 100644 --- a/qga/commands-posix.c +++ b/qga/commands-posix.c @@ -24,23 +24,12 @@ #include "qemu/base64.h" #include "qemu/cutils.h" #include "commands-common.h" -#include "block/nvme.h" #include "cutils.h" #ifdef HAVE_UTMPX #include <utmpx.h> #endif -#if defined(__linux__) -#include <mntent.h> -#include <sys/statvfs.h> -#include <linux/nvme_ioctl.h> - -#ifdef CONFIG_LIBUDEV -#include <libudev.h> -#endif -#endif - #ifdef HAVE_GETIFADDRS #include <arpa/inet.h> #include <sys/socket.h> @@ -59,7 +48,7 @@ #endif #endif -static void ga_wait_child(pid_t pid, int *status, Error **errp) +static bool ga_wait_child(pid_t pid, int *status, Error **errp) { pid_t rpid; @@ -70,10 +59,11 @@ static void ga_wait_child(pid_t pid, int *status, Error **errp) if (rpid == -1) { error_setg_errno(errp, errno, "failed to wait for child (pid: %d)", pid); - return; + return false; } g_assert(rpid == pid); + return true; } static ssize_t ga_pipe_read_str(int fd[2], char **str) @@ -178,8 +168,7 @@ static int ga_run_command(const char *argv[], const char *in_str, goto out; } - ga_wait_child(pid, &status, errp); - if (*errp) { + if (!ga_wait_child(pid, &status, errp)) { goto out; } @@ -842,1308 +831,6 @@ static void guest_fsfreeze_cleanup(void) } #endif -/* linux-specific implementations. avoid this if at all possible. */ -#if defined(__linux__) -#if defined(CONFIG_FSFREEZE) - -static char *get_pci_driver(char const *syspath, int pathlen, Error **errp) -{ - char *path; - char *dpath; - char *driver = NULL; - char buf[PATH_MAX]; - ssize_t len; - - path = g_strndup(syspath, pathlen); - dpath = g_strdup_printf("%s/driver", path); - len = readlink(dpath, buf, sizeof(buf) - 1); - if (len != -1) { - buf[len] = 0; - driver = g_path_get_basename(buf); - } - g_free(dpath); - g_free(path); - return driver; -} - -static int compare_uint(const void *_a, const void *_b) -{ - unsigned int a = *(unsigned int *)_a; - unsigned int b = *(unsigned int *)_b; - - return a < b ? -1 : a > b ? 1 : 0; -} - -/* Walk the specified sysfs and build a sorted list of host or ata numbers */ -static int build_hosts(char const *syspath, char const *host, bool ata, - unsigned int *hosts, int hosts_max, Error **errp) -{ - char *path; - DIR *dir; - struct dirent *entry; - int i = 0; - - path = g_strndup(syspath, host - syspath); - dir = opendir(path); - if (!dir) { - error_setg_errno(errp, errno, "opendir(\"%s\")", path); - g_free(path); - return -1; - } - - while (i < hosts_max) { - entry = readdir(dir); - if (!entry) { - break; - } - if (ata && sscanf(entry->d_name, "ata%d", hosts + i) == 1) { - ++i; - } else if (!ata && sscanf(entry->d_name, "host%d", hosts + i) == 1) { - ++i; - } - } - - qsort(hosts, i, sizeof(hosts[0]), compare_uint); - - g_free(path); - closedir(dir); - return i; -} - -/* - * Store disk device info for devices on the PCI bus. - * Returns true if information has been stored, or false for failure. - */ -static bool build_guest_fsinfo_for_pci_dev(char const *syspath, - GuestDiskAddress *disk, - Error **errp) -{ - unsigned int pci[4], host, hosts[8], tgt[3]; - int i, nhosts = 0, pcilen; - GuestPCIAddress *pciaddr = disk->pci_controller; - bool has_ata = false, has_host = false, has_tgt = false; - char *p, *q, *driver = NULL; - bool ret = false; - - p = strstr(syspath, "/devices/pci"); - if (!p || sscanf(p + 12, "%*x:%*x/%x:%x:%x.%x%n", - pci, pci + 1, pci + 2, pci + 3, &pcilen) < 4) { - g_debug("only pci device is supported: sysfs path '%s'", syspath); - return false; - } - - p += 12 + pcilen; - while (true) { - driver = get_pci_driver(syspath, p - syspath, errp); - if (driver && (g_str_equal(driver, "ata_piix") || - g_str_equal(driver, "sym53c8xx") || - g_str_equal(driver, "virtio-pci") || - g_str_equal(driver, "ahci") || - g_str_equal(driver, "nvme") || - g_str_equal(driver, "xhci_hcd") || - g_str_equal(driver, "ehci-pci"))) { - break; - } - - g_free(driver); - if (sscanf(p, "/%x:%x:%x.%x%n", - pci, pci + 1, pci + 2, pci + 3, &pcilen) == 4) { - p += pcilen; - continue; - } - - g_debug("unsupported driver or sysfs path '%s'", syspath); - return false; - } - - p = strstr(syspath, "/target"); - if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u", - tgt, tgt + 1, tgt + 2) == 3) { - has_tgt = true; - } - - p = strstr(syspath, "/ata"); - if (p) { - q = p + 4; - has_ata = true; - } else { - p = strstr(syspath, "/host"); - q = p + 5; - } - if (p && sscanf(q, "%u", &host) == 1) { - has_host = true; - nhosts = build_hosts(syspath, p, has_ata, hosts, - ARRAY_SIZE(hosts), errp); - if (nhosts < 0) { - goto cleanup; - } - } - - pciaddr->domain = pci[0]; - pciaddr->bus = pci[1]; - pciaddr->slot = pci[2]; - pciaddr->function = pci[3]; - - if (strcmp(driver, "ata_piix") == 0) { - /* a host per ide bus, target*:0:<unit>:0 */ - if (!has_host || !has_tgt) { - g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver); - goto cleanup; - } - for (i = 0; i < nhosts; i++) { - if (host == hosts[i]) { - disk->bus_type = GUEST_DISK_BUS_TYPE_IDE; - disk->bus = i; - disk->unit = tgt[1]; - break; - } - } - if (i >= nhosts) { - g_debug("no host for '%s' (driver '%s')", syspath, driver); - goto cleanup; - } - } else if (strcmp(driver, "sym53c8xx") == 0) { - /* scsi(LSI Logic): target*:0:<unit>:0 */ - if (!has_tgt) { - g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver); - goto cleanup; - } - disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI; - disk->unit = tgt[1]; - } else if (strcmp(driver, "virtio-pci") == 0) { - if (has_tgt) { - /* virtio-scsi: target*:0:0:<unit> */ - disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI; - disk->unit = tgt[2]; - } else { - /* virtio-blk: 1 disk per 1 device */ - disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO; - } - } else if (strcmp(driver, "ahci") == 0) { - /* ahci: 1 host per 1 unit */ - if (!has_host || !has_tgt) { - g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver); - goto cleanup; - } - for (i = 0; i < nhosts; i++) { - if (host == hosts[i]) { - disk->unit = i; - disk->bus_type = GUEST_DISK_BUS_TYPE_SATA; - break; - } - } - if (i >= nhosts) { - g_debug("no host for '%s' (driver '%s')", syspath, driver); - goto cleanup; - } - } else if (strcmp(driver, "nvme") == 0) { - disk->bus_type = GUEST_DISK_BUS_TYPE_NVME; - } else if (strcmp(driver, "ehci-pci") == 0 || strcmp(driver, "xhci_hcd") == 0) { - disk->bus_type = GUEST_DISK_BUS_TYPE_USB; - } else { - g_debug("unknown driver '%s' (sysfs path '%s')", driver, syspath); - goto cleanup; - } - - ret = true; - -cleanup: - g_free(driver); - return ret; -} - -/* - * Store disk device info for non-PCI virtio devices (for example s390x - * channel I/O devices). Returns true if information has been stored, or - * false for failure. - */ -static bool build_guest_fsinfo_for_nonpci_virtio(char const *syspath, - GuestDiskAddress *disk, - Error **errp) -{ - unsigned int tgt[3]; - char *p; - - if (!strstr(syspath, "/virtio") || !strstr(syspath, "/block")) { - g_debug("Unsupported virtio device '%s'", syspath); - return false; - } - - p = strstr(syspath, "/target"); - if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u", - &tgt[0], &tgt[1], &tgt[2]) == 3) { - /* virtio-scsi: target*:0:<target>:<unit> */ - disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI; - disk->bus = tgt[0]; - disk->target = tgt[1]; - disk->unit = tgt[2]; - } else { - /* virtio-blk: 1 disk per 1 device */ - disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO; - } - - return true; -} - -/* - * Store disk device info for CCW devices (s390x channel I/O devices). - * Returns true if information has been stored, or false for failure. - */ -static bool build_guest_fsinfo_for_ccw_dev(char const *syspath, - GuestDiskAddress *disk, - Error **errp) -{ - unsigned int cssid, ssid, subchno, devno; - char *p; - - p = strstr(syspath, "/devices/css"); - if (!p || sscanf(p + 12, "%*x/%x.%x.%x/%*x.%*x.%x/", - &cssid, &ssid, &subchno, &devno) < 4) { - g_debug("could not parse ccw device sysfs path: %s", syspath); - return false; - } - - disk->ccw_address = g_new0(GuestCCWAddress, 1); - disk->ccw_address->cssid = cssid; - disk->ccw_address->ssid = ssid; - disk->ccw_address->subchno = subchno; - disk->ccw_address->devno = devno; - - if (strstr(p, "/virtio")) { - build_guest_fsinfo_for_nonpci_virtio(syspath, disk, errp); - } - - return true; -} - -/* Store disk device info specified by @sysfs into @fs */ -static void build_guest_fsinfo_for_real_device(char const *syspath, - GuestFilesystemInfo *fs, - Error **errp) -{ - GuestDiskAddress *disk; - GuestPCIAddress *pciaddr; - bool has_hwinf; -#ifdef CONFIG_LIBUDEV - struct udev *udev = NULL; - struct udev_device *udevice = NULL; -#endif - - pciaddr = g_new0(GuestPCIAddress, 1); - pciaddr->domain = -1; /* -1 means field is invalid */ - pciaddr->bus = -1; - pciaddr->slot = -1; - pciaddr->function = -1; - - disk = g_new0(GuestDiskAddress, 1); - disk->pci_controller = pciaddr; - disk->bus_type = GUEST_DISK_BUS_TYPE_UNKNOWN; - -#ifdef CONFIG_LIBUDEV - udev = udev_new(); - udevice = udev_device_new_from_syspath(udev, syspath); - if (udev == NULL || udevice == NULL) { - g_debug("failed to query udev"); - } else { - const char *devnode, *serial; - devnode = udev_device_get_devnode(udevice); - if (devnode != NULL) { - disk->dev = g_strdup(devnode); - } - serial = udev_device_get_property_value(udevice, "ID_SERIAL"); - if (serial != NULL && *serial != 0) { - disk->serial = g_strdup(serial); - } - } - - udev_unref(udev); - udev_device_unref(udevice); -#endif - - if (strstr(syspath, "/devices/pci")) { - has_hwinf = build_guest_fsinfo_for_pci_dev(syspath, disk, errp); - } else if (strstr(syspath, "/devices/css")) { - has_hwinf = build_guest_fsinfo_for_ccw_dev(syspath, disk, errp); - } else if (strstr(syspath, "/virtio")) { - has_hwinf = build_guest_fsinfo_for_nonpci_virtio(syspath, disk, errp); - } else { - g_debug("Unsupported device type for '%s'", syspath); - has_hwinf = false; - } - - if (has_hwinf || disk->dev || disk->serial) { - QAPI_LIST_PREPEND(fs->disk, disk); - } else { - qapi_free_GuestDiskAddress(disk); - } -} - -static void build_guest_fsinfo_for_device(char const *devpath, - GuestFilesystemInfo *fs, - Error **errp); - -/* Store a list of slave devices of virtual volume specified by @syspath into - * @fs */ -static void build_guest_fsinfo_for_virtual_device(char const *syspath, - GuestFilesystemInfo *fs, - Error **errp) -{ - Error *err = NULL; - DIR *dir; - char *dirpath; - struct dirent *entry; - - dirpath = g_strdup_printf("%s/slaves", syspath); - dir = opendir(dirpath); - if (!dir) { - if (errno != ENOENT) { - error_setg_errno(errp, errno, "opendir(\"%s\")", dirpath); - } - g_free(dirpath); - return; - } - - for (;;) { - errno = 0; - entry = readdir(dir); - if (entry == NULL) { - if (errno) { - error_setg_errno(errp, errno, "readdir(\"%s\")", dirpath); - } - break; - } - - if (entry->d_type == DT_LNK) { - char *path; - - g_debug(" slave device '%s'", entry->d_name); - path = g_strdup_printf("%s/slaves/%s", syspath, entry->d_name); - build_guest_fsinfo_for_device(path, fs, &err); - g_free(path); - - if (err) { - error_propagate(errp, err); - break; - } - } - } - - g_free(dirpath); - closedir(dir); -} - -static bool is_disk_virtual(const char *devpath, Error **errp) -{ - g_autofree char *syspath = realpath(devpath, NULL); - - if (!syspath) { - error_setg_errno(errp, errno, "realpath(\"%s\")", devpath); - return false; - } - return strstr(syspath, "/devices/virtual/block/") != NULL; -} - -/* Dispatch to functions for virtual/real device */ -static void build_guest_fsinfo_for_device(char const *devpath, - GuestFilesystemInfo *fs, - Error **errp) -{ - ERRP_GUARD(); - g_autofree char *syspath = NULL; - bool is_virtual = false; - - syspath = realpath(devpath, NULL); - if (!syspath) { - if (errno != ENOENT) { - error_setg_errno(errp, errno, "realpath(\"%s\")", devpath); - return; - } - - /* ENOENT: This devpath may not exist because of container config */ - if (!fs->name) { - fs->name = g_path_get_basename(devpath); - } - return; - } - - if (!fs->name) { - fs->name = g_path_get_basename(syspath); - } - - g_debug(" parse sysfs path '%s'", syspath); - is_virtual = is_disk_virtual(syspath, errp); - if (*errp != NULL) { - return; - } - if (is_virtual) { - build_guest_fsinfo_for_virtual_device(syspath, fs, errp); - } else { - build_guest_fsinfo_for_real_device(syspath, fs, errp); - } -} - -#ifdef CONFIG_LIBUDEV - -/* - * Wrapper around build_guest_fsinfo_for_device() for getting just - * the disk address. - */ -static GuestDiskAddress *get_disk_address(const char *syspath, Error **errp) -{ - g_autoptr(GuestFilesystemInfo) fs = NULL; - - fs = g_new0(GuestFilesystemInfo, 1); - build_guest_fsinfo_for_device(syspath, fs, errp); - if (fs->disk != NULL) { - return g_steal_pointer(&fs->disk->value); - } - return NULL; -} - -static char *get_alias_for_syspath(const char *syspath) -{ - struct udev *udev = NULL; - struct udev_device *udevice = NULL; - char *ret = NULL; - - udev = udev_new(); - if (udev == NULL) { - g_debug("failed to query udev"); - goto out; - } - udevice = udev_device_new_from_syspath(udev, syspath); - if (udevice == NULL) { - g_debug("failed to query udev for path: %s", syspath); - goto out; - } else { - const char *alias = udev_device_get_property_value( - udevice, "DM_NAME"); - /* - * NULL means there was an error and empty string means there is no - * alias. In case of no alias we return NULL instead of empty string. - */ - if (alias == NULL) { - g_debug("failed to query udev for device alias for: %s", - syspath); - } else if (*alias != 0) { - ret = g_strdup(alias); - } - } - -out: - udev_unref(udev); - udev_device_unref(udevice); - return ret; -} - -static char *get_device_for_syspath(const char *syspath) -{ - struct udev *udev = NULL; - struct udev_device *udevice = NULL; - char *ret = NULL; - - udev = udev_new(); - if (udev == NULL) { - g_debug("failed to query udev"); - goto out; - } - udevice = udev_device_new_from_syspath(udev, syspath); - if (udevice == NULL) { - g_debug("failed to query udev for path: %s", syspath); - goto out; - } else { - ret = g_strdup(udev_device_get_devnode(udevice)); - } - -out: - udev_unref(udev); - udev_device_unref(udevice); - return ret; -} - -static void get_disk_deps(const char *disk_dir, GuestDiskInfo *disk) -{ - g_autofree char *deps_dir = NULL; - const gchar *dep; - GDir *dp_deps = NULL; - - /* List dependent disks */ - deps_dir = g_strdup_printf("%s/slaves", disk_dir); - g_debug(" listing entries in: %s", deps_dir); - dp_deps = g_dir_open(deps_dir, 0, NULL); - if (dp_deps == NULL) { - g_debug("failed to list entries in %s", deps_dir); - return; - } - disk->has_dependencies = true; - while ((dep = g_dir_read_name(dp_deps)) != NULL) { - g_autofree char *dep_dir = NULL; - char *dev_name; - - /* Add dependent disks */ - dep_dir = g_strdup_printf("%s/%s", deps_dir, dep); - dev_name = get_device_for_syspath(dep_dir); - if (dev_name != NULL) { - g_debug(" adding dependent device: %s", dev_name); - QAPI_LIST_PREPEND(disk->dependencies, dev_name); - } - } - g_dir_close(dp_deps); -} - -/* - * Detect partitions subdirectory, name is "<disk_name><number>" or - * "<disk_name>p<number>" - * - * @disk_name -- last component of /sys path (e.g. sda) - * @disk_dir -- sys path of the disk (e.g. /sys/block/sda) - * @disk_dev -- device node of the disk (e.g. /dev/sda) - */ -static GuestDiskInfoList *get_disk_partitions( - GuestDiskInfoList *list, - const char *disk_name, const char *disk_dir, - const char *disk_dev) -{ - GuestDiskInfoList *ret = list; - struct dirent *de_disk; - DIR *dp_disk = NULL; - size_t len = strlen(disk_name); - - dp_disk = opendir(disk_dir); - while ((de_disk = readdir(dp_disk)) != NULL) { - g_autofree char *partition_dir = NULL; - char *dev_name; - GuestDiskInfo *partition; - - if (!(de_disk->d_type & DT_DIR)) { - continue; - } - - if (!(strncmp(disk_name, de_disk->d_name, len) == 0 && - ((*(de_disk->d_name + len) == 'p' && - isdigit(*(de_disk->d_name + len + 1))) || - isdigit(*(de_disk->d_name + len))))) { - continue; - } - - partition_dir = g_strdup_printf("%s/%s", - disk_dir, de_disk->d_name); - dev_name = get_device_for_syspath(partition_dir); - if (dev_name == NULL) { - g_debug("Failed to get device name for syspath: %s", - disk_dir); - continue; - } - partition = g_new0(GuestDiskInfo, 1); - partition->name = dev_name; - partition->partition = true; - partition->has_dependencies = true; - /* Add parent disk as dependent for easier tracking of hierarchy */ - QAPI_LIST_PREPEND(partition->dependencies, g_strdup(disk_dev)); - - QAPI_LIST_PREPEND(ret, partition); - } - closedir(dp_disk); - - return ret; -} - -static void get_nvme_smart(GuestDiskInfo *disk) -{ - int fd; - GuestNVMeSmart *smart; - NvmeSmartLog log = {0}; - struct nvme_admin_cmd cmd = { - .opcode = NVME_ADM_CMD_GET_LOG_PAGE, - .nsid = NVME_NSID_BROADCAST, - .addr = (uintptr_t)&log, - .data_len = sizeof(log), - .cdw10 = NVME_LOG_SMART_INFO | (1 << 15) /* RAE bit */ - | (((sizeof(log) >> 2) - 1) << 16) - }; - - fd = qga_open_cloexec(disk->name, O_RDONLY, 0); - if (fd == -1) { - g_debug("Failed to open device: %s: %s", disk->name, g_strerror(errno)); - return; - } - - if (ioctl(fd, NVME_IOCTL_ADMIN_CMD, &cmd)) { - g_debug("Failed to get smart: %s: %s", disk->name, g_strerror(errno)); - close(fd); - return; - } - - disk->smart = g_new0(GuestDiskSmart, 1); - disk->smart->type = GUEST_DISK_BUS_TYPE_NVME; - - smart = &disk->smart->u.nvme; - smart->critical_warning = log.critical_warning; - smart->temperature = lduw_le_p(&log.temperature); /* unaligned field */ - smart->available_spare = log.available_spare; - smart->available_spare_threshold = log.available_spare_threshold; - smart->percentage_used = log.percentage_used; - smart->data_units_read_lo = le64_to_cpu(log.data_units_read[0]); - smart->data_units_read_hi = le64_to_cpu(log.data_units_read[1]); - smart->data_units_written_lo = le64_to_cpu(log.data_units_written[0]); - smart->data_units_written_hi = le64_to_cpu(log.data_units_written[1]); - smart->host_read_commands_lo = le64_to_cpu(log.host_read_commands[0]); - smart->host_read_commands_hi = le64_to_cpu(log.host_read_commands[1]); - smart->host_write_commands_lo = le64_to_cpu(log.host_write_commands[0]); - smart->host_write_commands_hi = le64_to_cpu(log.host_write_commands[1]); - smart->controller_busy_time_lo = le64_to_cpu(log.controller_busy_time[0]); - smart->controller_busy_time_hi = le64_to_cpu(log.controller_busy_time[1]); - smart->power_cycles_lo = le64_to_cpu(log.power_cycles[0]); - smart->power_cycles_hi = le64_to_cpu(log.power_cycles[1]); - smart->power_on_hours_lo = le64_to_cpu(log.power_on_hours[0]); - smart->power_on_hours_hi = le64_to_cpu(log.power_on_hours[1]); - smart->unsafe_shutdowns_lo = le64_to_cpu(log.unsafe_shutdowns[0]); - smart->unsafe_shutdowns_hi = le64_to_cpu(log.unsafe_shutdowns[1]); - smart->media_errors_lo = le64_to_cpu(log.media_errors[0]); - smart->media_errors_hi = le64_to_cpu(log.media_errors[1]); - smart->number_of_error_log_entries_lo = - le64_to_cpu(log.number_of_error_log_entries[0]); - smart->number_of_error_log_entries_hi = - le64_to_cpu(log.number_of_error_log_entries[1]); - - close(fd); -} - -static void get_disk_smart(GuestDiskInfo *disk) -{ - if (disk->address - && (disk->address->bus_type == GUEST_DISK_BUS_TYPE_NVME)) { - get_nvme_smart(disk); - } -} - -GuestDiskInfoList *qmp_guest_get_disks(Error **errp) -{ - GuestDiskInfoList *ret = NULL; - GuestDiskInfo *disk; - DIR *dp = NULL; - struct dirent *de = NULL; - - g_debug("listing /sys/block directory"); - dp = opendir("/sys/block"); - if (dp == NULL) { - error_setg_errno(errp, errno, "Can't open directory \"/sys/block\""); - return NULL; - } - while ((de = readdir(dp)) != NULL) { - g_autofree char *disk_dir = NULL, *line = NULL, - *size_path = NULL; - char *dev_name; - Error *local_err = NULL; - if (de->d_type != DT_LNK) { - g_debug(" skipping entry: %s", de->d_name); - continue; - } - - /* Check size and skip zero-sized disks */ - g_debug(" checking disk size"); - size_path = g_strdup_printf("/sys/block/%s/size", de->d_name); - if (!g_file_get_contents(size_path, &line, NULL, NULL)) { - g_debug(" failed to read disk size"); - continue; - } - if (g_strcmp0(line, "0\n") == 0) { - g_debug(" skipping zero-sized disk"); - continue; - } - - g_debug(" adding %s", de->d_name); - disk_dir = g_strdup_printf("/sys/block/%s", de->d_name); - dev_name = get_device_for_syspath(disk_dir); - if (dev_name == NULL) { - g_debug("Failed to get device name for syspath: %s", - disk_dir); - continue; - } - disk = g_new0(GuestDiskInfo, 1); - disk->name = dev_name; - disk->partition = false; - disk->alias = get_alias_for_syspath(disk_dir); - QAPI_LIST_PREPEND(ret, disk); - - /* Get address for non-virtual devices */ - bool is_virtual = is_disk_virtual(disk_dir, &local_err); - if (local_err != NULL) { - g_debug(" failed to check disk path, ignoring error: %s", - error_get_pretty(local_err)); - error_free(local_err); - local_err = NULL; - /* Don't try to get the address */ - is_virtual = true; - } - if (!is_virtual) { - disk->address = get_disk_address(disk_dir, &local_err); - if (local_err != NULL) { - g_debug(" failed to get device info, ignoring error: %s", - error_get_pretty(local_err)); - error_free(local_err); - local_err = NULL; - } - } - - get_disk_deps(disk_dir, disk); - get_disk_smart(disk); - ret = get_disk_partitions(ret, de->d_name, disk_dir, dev_name); - } - - closedir(dp); - - return ret; -} - -#else - -GuestDiskInfoList *qmp_guest_get_disks(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -#endif - -/* Return a list of the disk device(s)' info which @mount lies on */ -static GuestFilesystemInfo *build_guest_fsinfo(struct FsMount *mount, - Error **errp) -{ - GuestFilesystemInfo *fs = g_malloc0(sizeof(*fs)); - struct statvfs buf; - unsigned long used, nonroot_total, fr_size; - char *devpath = g_strdup_printf("/sys/dev/block/%u:%u", - mount->devmajor, mount->devminor); - - fs->mountpoint = g_strdup(mount->dirname); - fs->type = g_strdup(mount->devtype); - build_guest_fsinfo_for_device(devpath, fs, errp); - - if (statvfs(fs->mountpoint, &buf) == 0) { - fr_size = buf.f_frsize; - used = buf.f_blocks - buf.f_bfree; - nonroot_total = used + buf.f_bavail; - fs->used_bytes = used * fr_size; - fs->total_bytes = nonroot_total * fr_size; - fs->total_bytes_privileged = buf.f_blocks * fr_size; - - fs->has_total_bytes = true; - fs->has_total_bytes_privileged = true; - fs->has_used_bytes = true; - } - - g_free(devpath); - - return fs; -} - -GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp) -{ - FsMountList mounts; - struct FsMount *mount; - GuestFilesystemInfoList *ret = NULL; - Error *local_err = NULL; - - QTAILQ_INIT(&mounts); - if (!build_fs_mount_list(&mounts, &local_err)) { - error_propagate(errp, local_err); - return NULL; - } - - QTAILQ_FOREACH(mount, &mounts, next) { - g_debug("Building guest fsinfo for '%s'", mount->dirname); - - QAPI_LIST_PREPEND(ret, build_guest_fsinfo(mount, &local_err)); - if (local_err) { - error_propagate(errp, local_err); - qapi_free_GuestFilesystemInfoList(ret); - ret = NULL; - break; - } - } - - free_fs_mount_list(&mounts); - return ret; -} -#endif /* CONFIG_FSFREEZE */ - -#if defined(CONFIG_FSTRIM) -/* - * Walk list of mounted file systems in the guest, and trim them. - */ -GuestFilesystemTrimResponse * -qmp_guest_fstrim(bool has_minimum, int64_t minimum, Error **errp) -{ - GuestFilesystemTrimResponse *response; - GuestFilesystemTrimResult *result; - int ret = 0; - FsMountList mounts; - struct FsMount *mount; - int fd; - struct fstrim_range r; - - slog("guest-fstrim called"); - - QTAILQ_INIT(&mounts); - if (!build_fs_mount_list(&mounts, errp)) { - return NULL; - } - - response = g_malloc0(sizeof(*response)); - - QTAILQ_FOREACH(mount, &mounts, next) { - result = g_malloc0(sizeof(*result)); - result->path = g_strdup(mount->dirname); - - QAPI_LIST_PREPEND(response->paths, result); - - fd = qga_open_cloexec(mount->dirname, O_RDONLY, 0); - if (fd == -1) { - result->error = g_strdup_printf("failed to open: %s", - strerror(errno)); - continue; - } - - /* We try to cull filesystems we know won't work in advance, but other - * filesystems may not implement fstrim for less obvious reasons. - * These will report EOPNOTSUPP; while in some other cases ENOTTY - * will be reported (e.g. CD-ROMs). - * Any other error means an unexpected error. - */ - r.start = 0; - r.len = -1; - r.minlen = has_minimum ? minimum : 0; - ret = ioctl(fd, FITRIM, &r); - if (ret == -1) { - if (errno == ENOTTY || errno == EOPNOTSUPP) { - result->error = g_strdup("trim not supported"); - } else { - result->error = g_strdup_printf("failed to trim: %s", - strerror(errno)); - } - close(fd); - continue; - } - - result->has_minimum = true; - result->minimum = r.minlen; - result->has_trimmed = true; - result->trimmed = r.len; - close(fd); - } - - free_fs_mount_list(&mounts); - return response; -} -#endif /* CONFIG_FSTRIM */ - - -#define LINUX_SYS_STATE_FILE "/sys/power/state" -#define SUSPEND_SUPPORTED 0 -#define SUSPEND_NOT_SUPPORTED 1 - -typedef enum { - SUSPEND_MODE_DISK = 0, - SUSPEND_MODE_RAM = 1, - SUSPEND_MODE_HYBRID = 2, -} SuspendMode; - -/* - * Executes a command in a child process using g_spawn_sync, - * returning an int >= 0 representing the exit status of the - * process. - * - * If the program wasn't found in path, returns -1. - * - * If a problem happened when creating the child process, - * returns -1 and errp is set. - */ -static int run_process_child(const char *command[], Error **errp) -{ - int exit_status, spawn_flag; - GError *g_err = NULL; - bool success; - - spawn_flag = G_SPAWN_SEARCH_PATH | G_SPAWN_STDOUT_TO_DEV_NULL | - G_SPAWN_STDERR_TO_DEV_NULL; - - success = g_spawn_sync(NULL, (char **)command, NULL, spawn_flag, - NULL, NULL, NULL, NULL, - &exit_status, &g_err); - - if (success) { - return WEXITSTATUS(exit_status); - } - - if (g_err && (g_err->code != G_SPAWN_ERROR_NOENT)) { - error_setg(errp, "failed to create child process, error '%s'", - g_err->message); - } - - g_error_free(g_err); - return -1; -} - -static bool systemd_supports_mode(SuspendMode mode, Error **errp) -{ - const char *systemctl_args[3] = {"systemd-hibernate", "systemd-suspend", - "systemd-hybrid-sleep"}; - const char *cmd[4] = {"systemctl", "status", systemctl_args[mode], NULL}; - int status; - - status = run_process_child(cmd, errp); - - /* - * systemctl status uses LSB return codes so we can expect - * status > 0 and be ok. To assert if the guest has support - * for the selected suspend mode, status should be < 4. 4 is - * the code for unknown service status, the return value when - * the service does not exist. A common value is status = 3 - * (program is not running). - */ - if (status > 0 && status < 4) { - return true; - } - - return false; -} - -static void systemd_suspend(SuspendMode mode, Error **errp) -{ - Error *local_err = NULL; - const char *systemctl_args[3] = {"hibernate", "suspend", "hybrid-sleep"}; - const char *cmd[3] = {"systemctl", systemctl_args[mode], NULL}; - int status; - - status = run_process_child(cmd, &local_err); - - if (status == 0) { - return; - } - - if ((status == -1) && !local_err) { - error_setg(errp, "the helper program 'systemctl %s' was not found", - systemctl_args[mode]); - return; - } - - if (local_err) { - error_propagate(errp, local_err); - } else { - error_setg(errp, "the helper program 'systemctl %s' returned an " - "unexpected exit status code (%d)", - systemctl_args[mode], status); - } -} - -static bool pmutils_supports_mode(SuspendMode mode, Error **errp) -{ - Error *local_err = NULL; - const char *pmutils_args[3] = {"--hibernate", "--suspend", - "--suspend-hybrid"}; - const char *cmd[3] = {"pm-is-supported", pmutils_args[mode], NULL}; - int status; - - status = run_process_child(cmd, &local_err); - - if (status == SUSPEND_SUPPORTED) { - return true; - } - - if ((status == -1) && !local_err) { - return false; - } - - if (local_err) { - error_propagate(errp, local_err); - } else { - error_setg(errp, - "the helper program '%s' returned an unexpected exit" - " status code (%d)", "pm-is-supported", status); - } - - return false; -} - -static void pmutils_suspend(SuspendMode mode, Error **errp) -{ - Error *local_err = NULL; - const char *pmutils_binaries[3] = {"pm-hibernate", "pm-suspend", - "pm-suspend-hybrid"}; - const char *cmd[2] = {pmutils_binaries[mode], NULL}; - int status; - - status = run_process_child(cmd, &local_err); - - if (status == 0) { - return; - } - - if ((status == -1) && !local_err) { - error_setg(errp, "the helper program '%s' was not found", - pmutils_binaries[mode]); - return; - } - - if (local_err) { - error_propagate(errp, local_err); - } else { - error_setg(errp, - "the helper program '%s' returned an unexpected exit" - " status code (%d)", pmutils_binaries[mode], status); - } -} - -static bool linux_sys_state_supports_mode(SuspendMode mode, Error **errp) -{ - const char *sysfile_strs[3] = {"disk", "mem", NULL}; - const char *sysfile_str = sysfile_strs[mode]; - char buf[32]; /* hopefully big enough */ - int fd; - ssize_t ret; - - if (!sysfile_str) { - error_setg(errp, "unknown guest suspend mode"); - return false; - } - - fd = open(LINUX_SYS_STATE_FILE, O_RDONLY); - if (fd < 0) { - return false; - } - - ret = read(fd, buf, sizeof(buf) - 1); - close(fd); - if (ret <= 0) { - return false; - } - buf[ret] = '\0'; - - if (strstr(buf, sysfile_str)) { - return true; - } - return false; -} - -static void linux_sys_state_suspend(SuspendMode mode, Error **errp) -{ - g_autoptr(GError) local_gerr = NULL; - const char *sysfile_strs[3] = {"disk", "mem", NULL}; - const char *sysfile_str = sysfile_strs[mode]; - - if (!sysfile_str) { - error_setg(errp, "unknown guest suspend mode"); - return; - } - - if (!g_file_set_contents(LINUX_SYS_STATE_FILE, sysfile_str, - -1, &local_gerr)) { - error_setg(errp, "suspend: cannot write to '%s': %s", - LINUX_SYS_STATE_FILE, local_gerr->message); - return; - } -} - -static void guest_suspend(SuspendMode mode, Error **errp) -{ - Error *local_err = NULL; - bool mode_supported = false; - - if (systemd_supports_mode(mode, &local_err)) { - mode_supported = true; - systemd_suspend(mode, &local_err); - - if (!local_err) { - return; - } - } - - error_free(local_err); - local_err = NULL; - - if (pmutils_supports_mode(mode, &local_err)) { - mode_supported = true; - pmutils_suspend(mode, &local_err); - - if (!local_err) { - return; - } - } - - error_free(local_err); - local_err = NULL; - - if (linux_sys_state_supports_mode(mode, &local_err)) { - mode_supported = true; - linux_sys_state_suspend(mode, &local_err); - } - - if (!mode_supported) { - error_free(local_err); - error_setg(errp, - "the requested suspend mode is not supported by the guest"); - } else { - error_propagate(errp, local_err); - } -} - -void qmp_guest_suspend_disk(Error **errp) -{ - guest_suspend(SUSPEND_MODE_DISK, errp); -} - -void qmp_guest_suspend_ram(Error **errp) -{ - guest_suspend(SUSPEND_MODE_RAM, errp); -} - -void qmp_guest_suspend_hybrid(Error **errp) -{ - guest_suspend(SUSPEND_MODE_HYBRID, errp); -} - -/* Transfer online/offline status between @vcpu and the guest system. - * - * On input either @errp or *@errp must be NULL. - * - * In system-to-@vcpu direction, the following @vcpu fields are accessed: - * - R: vcpu->logical_id - * - W: vcpu->online - * - W: vcpu->can_offline - * - * In @vcpu-to-system direction, the following @vcpu fields are accessed: - * - R: vcpu->logical_id - * - R: vcpu->online - * - * Written members remain unmodified on error. - */ -static void transfer_vcpu(GuestLogicalProcessor *vcpu, bool sys2vcpu, - char *dirpath, Error **errp) -{ - int fd; - int res; - int dirfd; - static const char fn[] = "online"; - - dirfd = open(dirpath, O_RDONLY | O_DIRECTORY); - if (dirfd == -1) { - error_setg_errno(errp, errno, "open(\"%s\")", dirpath); - return; - } - - fd = openat(dirfd, fn, sys2vcpu ? O_RDONLY : O_RDWR); - if (fd == -1) { - if (errno != ENOENT) { - error_setg_errno(errp, errno, "open(\"%s/%s\")", dirpath, fn); - } else if (sys2vcpu) { - vcpu->online = true; - vcpu->can_offline = false; - } else if (!vcpu->online) { - error_setg(errp, "logical processor #%" PRId64 " can't be " - "offlined", vcpu->logical_id); - } /* otherwise pretend successful re-onlining */ - } else { - unsigned char status; - - res = pread(fd, &status, 1, 0); - if (res == -1) { - error_setg_errno(errp, errno, "pread(\"%s/%s\")", dirpath, fn); - } else if (res == 0) { - error_setg(errp, "pread(\"%s/%s\"): unexpected EOF", dirpath, - fn); - } else if (sys2vcpu) { - vcpu->online = (status != '0'); - vcpu->can_offline = true; - } else if (vcpu->online != (status != '0')) { - status = '0' + vcpu->online; - if (pwrite(fd, &status, 1, 0) == -1) { - error_setg_errno(errp, errno, "pwrite(\"%s/%s\")", dirpath, - fn); - } - } /* otherwise pretend successful re-(on|off)-lining */ - - res = close(fd); - g_assert(res == 0); - } - - res = close(dirfd); - g_assert(res == 0); -} - -GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp) -{ - GuestLogicalProcessorList *head, **tail; - const char *cpu_dir = "/sys/devices/system/cpu"; - const gchar *line; - g_autoptr(GDir) cpu_gdir = NULL; - Error *local_err = NULL; - - head = NULL; - tail = &head; - cpu_gdir = g_dir_open(cpu_dir, 0, NULL); - - if (cpu_gdir == NULL) { - error_setg_errno(errp, errno, "failed to list entries: %s", cpu_dir); - return NULL; - } - - while (local_err == NULL && (line = g_dir_read_name(cpu_gdir)) != NULL) { - GuestLogicalProcessor *vcpu; - int64_t id; - if (sscanf(line, "cpu%" PRId64, &id)) { - g_autofree char *path = g_strdup_printf("/sys/devices/system/cpu/" - "cpu%" PRId64 "/", id); - vcpu = g_malloc0(sizeof *vcpu); - vcpu->logical_id = id; - vcpu->has_can_offline = true; /* lolspeak ftw */ - transfer_vcpu(vcpu, true, path, &local_err); - QAPI_LIST_APPEND(tail, vcpu); - } - } - - if (local_err == NULL) { - /* there's no guest with zero VCPUs */ - g_assert(head != NULL); - return head; - } - - qapi_free_GuestLogicalProcessorList(head); - error_propagate(errp, local_err); - return NULL; -} - -int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp) -{ - int64_t processed; - Error *local_err = NULL; - - processed = 0; - while (vcpus != NULL) { - char *path = g_strdup_printf("/sys/devices/system/cpu/cpu%" PRId64 "/", - vcpus->value->logical_id); - - transfer_vcpu(vcpus->value, false, path, &local_err); - g_free(path); - if (local_err != NULL) { - break; - } - ++processed; - vcpus = vcpus->next; - } - - if (local_err != NULL) { - if (processed == 0) { - error_propagate(errp, local_err); - } else { - error_free(local_err); - } - } - - return processed; -} -#endif /* __linux__ */ - #if defined(__linux__) || defined(__FreeBSD__) void qmp_guest_set_user_password(const char *username, const char *password, @@ -2190,574 +877,8 @@ void qmp_guest_set_user_password(const char *username, return; } } -#else /* __linux__ || __FreeBSD__ */ -void qmp_guest_set_user_password(const char *username, - const char *password, - bool crypted, - Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); -} #endif /* __linux__ || __FreeBSD__ */ -#ifdef __linux__ -static void ga_read_sysfs_file(int dirfd, const char *pathname, char *buf, - int size, Error **errp) -{ - int fd; - int res; - - errno = 0; - fd = openat(dirfd, pathname, O_RDONLY); - if (fd == -1) { - error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname); - return; - } - - res = pread(fd, buf, size, 0); - if (res == -1) { - error_setg_errno(errp, errno, "pread sysfs file \"%s\"", pathname); - } else if (res == 0) { - error_setg(errp, "pread sysfs file \"%s\": unexpected EOF", pathname); - } - close(fd); -} - -static void ga_write_sysfs_file(int dirfd, const char *pathname, - const char *buf, int size, Error **errp) -{ - int fd; - - errno = 0; - fd = openat(dirfd, pathname, O_WRONLY); - if (fd == -1) { - error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname); - return; - } - - if (pwrite(fd, buf, size, 0) == -1) { - error_setg_errno(errp, errno, "pwrite sysfs file \"%s\"", pathname); - } - - close(fd); -} - -/* Transfer online/offline status between @mem_blk and the guest system. - * - * On input either @errp or *@errp must be NULL. - * - * In system-to-@mem_blk direction, the following @mem_blk fields are accessed: - * - R: mem_blk->phys_index - * - W: mem_blk->online - * - W: mem_blk->can_offline - * - * In @mem_blk-to-system direction, the following @mem_blk fields are accessed: - * - R: mem_blk->phys_index - * - R: mem_blk->online - *- R: mem_blk->can_offline - * Written members remain unmodified on error. - */ -static void transfer_memory_block(GuestMemoryBlock *mem_blk, bool sys2memblk, - GuestMemoryBlockResponse *result, - Error **errp) -{ - char *dirpath; - int dirfd; - char *status; - Error *local_err = NULL; - - if (!sys2memblk) { - DIR *dp; - - if (!result) { - error_setg(errp, "Internal error, 'result' should not be NULL"); - return; - } - errno = 0; - dp = opendir("/sys/devices/system/memory/"); - /* if there is no 'memory' directory in sysfs, - * we think this VM does not support online/offline memory block, - * any other solution? - */ - if (!dp) { - if (errno == ENOENT) { - result->response = - GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED; - } - goto out1; - } - closedir(dp); - } - - dirpath = g_strdup_printf("/sys/devices/system/memory/memory%" PRId64 "/", - mem_blk->phys_index); - dirfd = open(dirpath, O_RDONLY | O_DIRECTORY); - if (dirfd == -1) { - if (sys2memblk) { - error_setg_errno(errp, errno, "open(\"%s\")", dirpath); - } else { - if (errno == ENOENT) { - result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_NOT_FOUND; - } else { - result->response = - GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED; - } - } - g_free(dirpath); - goto out1; - } - g_free(dirpath); - - status = g_malloc0(10); - ga_read_sysfs_file(dirfd, "state", status, 10, &local_err); - if (local_err) { - /* treat with sysfs file that not exist in old kernel */ - if (errno == ENOENT) { - error_free(local_err); - if (sys2memblk) { - mem_blk->online = true; - mem_blk->can_offline = false; - } else if (!mem_blk->online) { - result->response = - GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED; - } - } else { - if (sys2memblk) { - error_propagate(errp, local_err); - } else { - error_free(local_err); - result->response = - GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED; - } - } - goto out2; - } - - if (sys2memblk) { - char removable = '0'; - - mem_blk->online = (strncmp(status, "online", 6) == 0); - - ga_read_sysfs_file(dirfd, "removable", &removable, 1, &local_err); - if (local_err) { - /* if no 'removable' file, it doesn't support offline mem blk */ - if (errno == ENOENT) { - error_free(local_err); - mem_blk->can_offline = false; - } else { - error_propagate(errp, local_err); - } - } else { - mem_blk->can_offline = (removable != '0'); - } - } else { - if (mem_blk->online != (strncmp(status, "online", 6) == 0)) { - const char *new_state = mem_blk->online ? "online" : "offline"; - - ga_write_sysfs_file(dirfd, "state", new_state, strlen(new_state), - &local_err); - if (local_err) { - error_free(local_err); - result->response = - GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED; - goto out2; - } - - result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_SUCCESS; - result->has_error_code = false; - } /* otherwise pretend successful re-(on|off)-lining */ - } - g_free(status); - close(dirfd); - return; - -out2: - g_free(status); - close(dirfd); -out1: - if (!sys2memblk) { - result->has_error_code = true; - result->error_code = errno; - } -} - -GuestMemoryBlockList *qmp_guest_get_memory_blocks(Error **errp) -{ - GuestMemoryBlockList *head, **tail; - Error *local_err = NULL; - struct dirent *de; - DIR *dp; - - head = NULL; - tail = &head; - - dp = opendir("/sys/devices/system/memory/"); - if (!dp) { - /* it's ok if this happens to be a system that doesn't expose - * memory blocks via sysfs, but otherwise we should report - * an error - */ - if (errno != ENOENT) { - error_setg_errno(errp, errno, "Can't open directory" - "\"/sys/devices/system/memory/\""); - } - return NULL; - } - - /* Note: the phys_index of memory block may be discontinuous, - * this is because a memblk is the unit of the Sparse Memory design, which - * allows discontinuous memory ranges (ex. NUMA), so here we should - * traverse the memory block directory. - */ - while ((de = readdir(dp)) != NULL) { - GuestMemoryBlock *mem_blk; - - if ((strncmp(de->d_name, "memory", 6) != 0) || - !(de->d_type & DT_DIR)) { - continue; - } - - mem_blk = g_malloc0(sizeof *mem_blk); - /* The d_name is "memoryXXX", phys_index is block id, same as XXX */ - mem_blk->phys_index = strtoul(&de->d_name[6], NULL, 10); - mem_blk->has_can_offline = true; /* lolspeak ftw */ - transfer_memory_block(mem_blk, true, NULL, &local_err); - if (local_err) { - break; - } - - QAPI_LIST_APPEND(tail, mem_blk); - } - - closedir(dp); - if (local_err == NULL) { - /* there's no guest with zero memory blocks */ - if (head == NULL) { - error_setg(errp, "guest reported zero memory blocks!"); - } - return head; - } - - qapi_free_GuestMemoryBlockList(head); - error_propagate(errp, local_err); - return NULL; -} - -GuestMemoryBlockResponseList * -qmp_guest_set_memory_blocks(GuestMemoryBlockList *mem_blks, Error **errp) -{ - GuestMemoryBlockResponseList *head, **tail; - Error *local_err = NULL; - - head = NULL; - tail = &head; - - while (mem_blks != NULL) { - GuestMemoryBlockResponse *result; - GuestMemoryBlock *current_mem_blk = mem_blks->value; - - result = g_malloc0(sizeof(*result)); - result->phys_index = current_mem_blk->phys_index; - transfer_memory_block(current_mem_blk, false, result, &local_err); - if (local_err) { /* should never happen */ - goto err; - } - - QAPI_LIST_APPEND(tail, result); - mem_blks = mem_blks->next; - } - - return head; -err: - qapi_free_GuestMemoryBlockResponseList(head); - error_propagate(errp, local_err); - return NULL; -} - -GuestMemoryBlockInfo *qmp_guest_get_memory_block_info(Error **errp) -{ - Error *local_err = NULL; - char *dirpath; - int dirfd; - char *buf; - GuestMemoryBlockInfo *info; - - dirpath = g_strdup_printf("/sys/devices/system/memory/"); - dirfd = open(dirpath, O_RDONLY | O_DIRECTORY); - if (dirfd == -1) { - error_setg_errno(errp, errno, "open(\"%s\")", dirpath); - g_free(dirpath); - return NULL; - } - g_free(dirpath); - - buf = g_malloc0(20); - ga_read_sysfs_file(dirfd, "block_size_bytes", buf, 20, &local_err); - close(dirfd); - if (local_err) { - g_free(buf); - error_propagate(errp, local_err); - return NULL; - } - - info = g_new0(GuestMemoryBlockInfo, 1); - info->size = strtol(buf, NULL, 16); /* the unit is bytes */ - - g_free(buf); - - return info; -} - -#define MAX_NAME_LEN 128 -static GuestDiskStatsInfoList *guest_get_diskstats(Error **errp) -{ -#ifdef CONFIG_LINUX - GuestDiskStatsInfoList *head = NULL, **tail = &head; - const char *diskstats = "/proc/diskstats"; - FILE *fp; - size_t n; - char *line = NULL; - - fp = fopen(diskstats, "r"); - if (fp == NULL) { - error_setg_errno(errp, errno, "open(\"%s\")", diskstats); - return NULL; - } - - while (getline(&line, &n, fp) != -1) { - g_autofree GuestDiskStatsInfo *diskstatinfo = NULL; - g_autofree GuestDiskStats *diskstat = NULL; - char dev_name[MAX_NAME_LEN]; - unsigned int ios_pgr, tot_ticks, rq_ticks, wr_ticks, dc_ticks, fl_ticks; - unsigned long rd_ios, rd_merges_or_rd_sec, rd_ticks_or_wr_sec, wr_ios; - unsigned long wr_merges, rd_sec_or_wr_ios, wr_sec; - unsigned long dc_ios, dc_merges, dc_sec, fl_ios; - unsigned int major, minor; - int i; - - i = sscanf(line, "%u %u %s %lu %lu %lu" - "%lu %lu %lu %lu %u %u %u %u" - "%lu %lu %lu %u %lu %u", - &major, &minor, dev_name, - &rd_ios, &rd_merges_or_rd_sec, &rd_sec_or_wr_ios, - &rd_ticks_or_wr_sec, &wr_ios, &wr_merges, &wr_sec, - &wr_ticks, &ios_pgr, &tot_ticks, &rq_ticks, - &dc_ios, &dc_merges, &dc_sec, &dc_ticks, - &fl_ios, &fl_ticks); - - if (i < 7) { - continue; - } - - diskstatinfo = g_new0(GuestDiskStatsInfo, 1); - diskstatinfo->name = g_strdup(dev_name); - diskstatinfo->major = major; - diskstatinfo->minor = minor; - - diskstat = g_new0(GuestDiskStats, 1); - if (i == 7) { - diskstat->has_read_ios = true; - diskstat->read_ios = rd_ios; - diskstat->has_read_sectors = true; - diskstat->read_sectors = rd_merges_or_rd_sec; - diskstat->has_write_ios = true; - diskstat->write_ios = rd_sec_or_wr_ios; - diskstat->has_write_sectors = true; - diskstat->write_sectors = rd_ticks_or_wr_sec; - } - if (i >= 14) { - diskstat->has_read_ios = true; - diskstat->read_ios = rd_ios; - diskstat->has_read_sectors = true; - diskstat->read_sectors = rd_sec_or_wr_ios; - diskstat->has_read_merges = true; - diskstat->read_merges = rd_merges_or_rd_sec; - diskstat->has_read_ticks = true; - diskstat->read_ticks = rd_ticks_or_wr_sec; - diskstat->has_write_ios = true; - diskstat->write_ios = wr_ios; - diskstat->has_write_sectors = true; - diskstat->write_sectors = wr_sec; - diskstat->has_write_merges = true; - diskstat->write_merges = wr_merges; - diskstat->has_write_ticks = true; - diskstat->write_ticks = wr_ticks; - diskstat->has_ios_pgr = true; - diskstat->ios_pgr = ios_pgr; - diskstat->has_total_ticks = true; - diskstat->total_ticks = tot_ticks; - diskstat->has_weight_ticks = true; - diskstat->weight_ticks = rq_ticks; - } - if (i >= 18) { - diskstat->has_discard_ios = true; - diskstat->discard_ios = dc_ios; - diskstat->has_discard_merges = true; - diskstat->discard_merges = dc_merges; - diskstat->has_discard_sectors = true; - diskstat->discard_sectors = dc_sec; - diskstat->has_discard_ticks = true; - diskstat->discard_ticks = dc_ticks; - } - if (i >= 20) { - diskstat->has_flush_ios = true; - diskstat->flush_ios = fl_ios; - diskstat->has_flush_ticks = true; - diskstat->flush_ticks = fl_ticks; - } - - diskstatinfo->stats = g_steal_pointer(&diskstat); - QAPI_LIST_APPEND(tail, diskstatinfo); - diskstatinfo = NULL; - } - free(line); - fclose(fp); - return head; -#else - g_debug("disk stats reporting available only for Linux"); - return NULL; -#endif -} - -GuestDiskStatsInfoList *qmp_guest_get_diskstats(Error **errp) -{ - return guest_get_diskstats(errp); -} - -GuestCpuStatsList *qmp_guest_get_cpustats(Error **errp) -{ - GuestCpuStatsList *head = NULL, **tail = &head; - const char *cpustats = "/proc/stat"; - int clk_tck = sysconf(_SC_CLK_TCK); - FILE *fp; - size_t n; - char *line = NULL; - - fp = fopen(cpustats, "r"); - if (fp == NULL) { - error_setg_errno(errp, errno, "open(\"%s\")", cpustats); - return NULL; - } - - while (getline(&line, &n, fp) != -1) { - GuestCpuStats *cpustat = NULL; - GuestLinuxCpuStats *linuxcpustat; - int i; - unsigned long user, system, idle, iowait, irq, softirq, steal, guest; - unsigned long nice, guest_nice; - char name[64]; - - i = sscanf(line, "%s %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu", - name, &user, &nice, &system, &idle, &iowait, &irq, &softirq, - &steal, &guest, &guest_nice); - - /* drop "cpu 1 2 3 ...", get "cpuX 1 2 3 ..." only */ - if ((i == EOF) || strncmp(name, "cpu", 3) || (name[3] == '\0')) { - continue; - } - - if (i < 5) { - slog("Parsing cpu stat from %s failed, see \"man proc\"", cpustats); - break; - } - - cpustat = g_new0(GuestCpuStats, 1); - cpustat->type = GUEST_CPU_STATS_TYPE_LINUX; - - linuxcpustat = &cpustat->u.q_linux; - linuxcpustat->cpu = atoi(&name[3]); - linuxcpustat->user = user * 1000 / clk_tck; - linuxcpustat->nice = nice * 1000 / clk_tck; - linuxcpustat->system = system * 1000 / clk_tck; - linuxcpustat->idle = idle * 1000 / clk_tck; - - if (i > 5) { - linuxcpustat->has_iowait = true; - linuxcpustat->iowait = iowait * 1000 / clk_tck; - } - - if (i > 6) { - linuxcpustat->has_irq = true; - linuxcpustat->irq = irq * 1000 / clk_tck; - linuxcpustat->has_softirq = true; - linuxcpustat->softirq = softirq * 1000 / clk_tck; - } - - if (i > 8) { - linuxcpustat->has_steal = true; - linuxcpustat->steal = steal * 1000 / clk_tck; - } - - if (i > 9) { - linuxcpustat->has_guest = true; - linuxcpustat->guest = guest * 1000 / clk_tck; - } - - if (i > 10) { - linuxcpustat->has_guest = true; - linuxcpustat->guest = guest * 1000 / clk_tck; - linuxcpustat->has_guestnice = true; - linuxcpustat->guestnice = guest_nice * 1000 / clk_tck; - } - - QAPI_LIST_APPEND(tail, cpustat); - } - - free(line); - fclose(fp); - return head; -} - -#else /* defined(__linux__) */ - -void qmp_guest_suspend_disk(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); -} - -void qmp_guest_suspend_ram(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); -} - -void qmp_guest_suspend_hybrid(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); -} - -GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return -1; -} - -GuestMemoryBlockList *qmp_guest_get_memory_blocks(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestMemoryBlockResponseList * -qmp_guest_set_memory_blocks(GuestMemoryBlockList *mem_blks, Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestMemoryBlockInfo *qmp_guest_get_memory_block_info(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -#endif - #ifdef HAVE_GETIFADDRS static GuestNetworkInterface * guest_find_interface(GuestNetworkInterfaceList *head, @@ -3013,131 +1134,8 @@ error: return NULL; } -#else - -GuestNetworkInterfaceList *qmp_guest_network_get_interfaces(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - #endif /* HAVE_GETIFADDRS */ -#if !defined(CONFIG_FSFREEZE) - -GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestFsfreezeStatus qmp_guest_fsfreeze_status(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - - return 0; -} - -int64_t qmp_guest_fsfreeze_freeze(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - - return 0; -} - -int64_t qmp_guest_fsfreeze_freeze_list(bool has_mountpoints, - strList *mountpoints, - Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - - return 0; -} - -int64_t qmp_guest_fsfreeze_thaw(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - - return 0; -} - -GuestDiskInfoList *qmp_guest_get_disks(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestDiskStatsInfoList *qmp_guest_get_diskstats(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestCpuStatsList *qmp_guest_get_cpustats(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -#endif /* CONFIG_FSFREEZE */ - -#if !defined(CONFIG_FSTRIM) -GuestFilesystemTrimResponse * -qmp_guest_fstrim(bool has_minimum, int64_t minimum, Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} -#endif - -/* add unsupported commands to the list of blocked RPCs */ -GList *ga_command_init_blockedrpcs(GList *blockedrpcs) -{ -#if !defined(__linux__) - { - const char *list[] = { - "guest-suspend-disk", "guest-suspend-ram", - "guest-suspend-hybrid", "guest-get-vcpus", "guest-set-vcpus", - "guest-get-memory-blocks", "guest-set-memory-blocks", - "guest-get-memory-block-size", "guest-get-memory-block-info", - NULL}; - char **p = (char **)list; - - while (*p) { - blockedrpcs = g_list_append(blockedrpcs, g_strdup(*p++)); - } - } -#endif - -#if !defined(HAVE_GETIFADDRS) - blockedrpcs = g_list_append(blockedrpcs, - g_strdup("guest-network-get-interfaces")); -#endif - -#if !defined(CONFIG_FSFREEZE) - { - const char *list[] = { - "guest-get-fsinfo", "guest-fsfreeze-status", - "guest-fsfreeze-freeze", "guest-fsfreeze-freeze-list", - "guest-fsfreeze-thaw", "guest-get-fsinfo", - "guest-get-disks", NULL}; - char **p = (char **)list; - - while (*p) { - blockedrpcs = g_list_append(blockedrpcs, g_strdup(*p++)); - } - } -#endif - -#if !defined(CONFIG_FSTRIM) - blockedrpcs = g_list_append(blockedrpcs, g_strdup("guest-fstrim")); -#endif - - blockedrpcs = g_list_append(blockedrpcs, g_strdup("guest-get-devices")); - - return blockedrpcs; -} - /* register init/cleanup routines for stateful command groups */ void ga_command_state_init(GAState *s, GACommandState *cs) { @@ -3200,15 +1198,7 @@ GuestUserList *qmp_guest_get_users(Error **errp) return head; } -#else - -GuestUserList *qmp_guest_get_users(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -#endif +#endif /* HAVE_UTMPX */ /* Replace escaped special characters with their real values. The replacement * is done in place -- returned value is in the original string. @@ -3345,13 +1335,6 @@ GuestOSInfo *qmp_guest_get_osinfo(Error **errp) return info; } -GuestDeviceInfoList *qmp_guest_get_devices(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - - return NULL; -} - #ifndef HOST_NAME_MAX # ifdef _POSIX_HOST_NAME_MAX # define HOST_NAME_MAX _POSIX_HOST_NAME_MAX diff --git a/qga/commands-win32.c b/qga/commands-win32.c index 0d1b836e87..61b36da469 100644 --- a/qga/commands-win32.c +++ b/qga/commands-win32.c @@ -1203,7 +1203,7 @@ GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp) GuestFsfreezeStatus qmp_guest_fsfreeze_status(Error **errp) { if (!vss_initialized()) { - error_setg(errp, QERR_UNSUPPORTED); + error_setg(errp, "fsfreeze not possible as VSS failed to initialize"); return 0; } @@ -1231,7 +1231,7 @@ int64_t qmp_guest_fsfreeze_freeze_list(bool has_mountpoints, Error *local_err = NULL; if (!vss_initialized()) { - error_setg(errp, QERR_UNSUPPORTED); + error_setg(errp, "fsfreeze not possible as VSS failed to initialize"); return 0; } @@ -1266,7 +1266,7 @@ int64_t qmp_guest_fsfreeze_thaw(Error **errp) int i; if (!vss_initialized()) { - error_setg(errp, QERR_UNSUPPORTED); + error_setg(errp, "fsfreeze not possible as VSS failed to initialize"); return 0; } @@ -1494,11 +1494,6 @@ out: } } -void qmp_guest_suspend_hybrid(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); -} - static IP_ADAPTER_ADDRESSES *guest_get_adapters_addresses(Error **errp) { IP_ADAPTER_ADDRESSES *adptr_addrs = NULL; @@ -1862,12 +1857,6 @@ GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp) return NULL; } -int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return -1; -} - static gchar * get_net_error_message(gint error) { @@ -1969,55 +1958,6 @@ done: g_free(rawpasswddata); } -GuestMemoryBlockList *qmp_guest_get_memory_blocks(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestMemoryBlockResponseList * -qmp_guest_set_memory_blocks(GuestMemoryBlockList *mem_blks, Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestMemoryBlockInfo *qmp_guest_get_memory_block_info(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -/* add unsupported commands to the list of blocked RPCs */ -GList *ga_command_init_blockedrpcs(GList *blockedrpcs) -{ - const char *list_unsupported[] = { - "guest-suspend-hybrid", - "guest-set-vcpus", - "guest-get-memory-blocks", "guest-set-memory-blocks", - "guest-get-memory-block-size", "guest-get-memory-block-info", - NULL}; - char **p = (char **)list_unsupported; - - while (*p) { - blockedrpcs = g_list_append(blockedrpcs, g_strdup(*p++)); - } - - if (!vss_init(true)) { - g_debug("vss_init failed, vss commands are going to be disabled"); - const char *list[] = { - "guest-get-fsinfo", "guest-fsfreeze-status", - "guest-fsfreeze-freeze", "guest-fsfreeze-thaw", NULL}; - p = (char **)list; - - while (*p) { - blockedrpcs = g_list_append(blockedrpcs, g_strdup(*p++)); - } - } - - return blockedrpcs; -} - /* register init/cleanup routines for stateful command groups */ void ga_command_state_init(GAState *s, GACommandState *cs) { @@ -2505,15 +2445,3 @@ char *qga_get_host_name(Error **errp) return g_utf16_to_utf8(tmp, size, NULL, NULL, NULL); } - -GuestDiskStatsInfoList *qmp_guest_get_diskstats(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} - -GuestCpuStatsList *qmp_guest_get_cpustats(Error **errp) -{ - error_setg(errp, QERR_UNSUPPORTED); - return NULL; -} diff --git a/qga/main.c b/qga/main.c index f4d5f15bb3..b8f7b1e4a3 100644 --- a/qga/main.c +++ b/qga/main.c @@ -70,6 +70,28 @@ typedef struct GAPersistentState { typedef struct GAConfig GAConfig; +struct GAConfig { + char *channel_path; + char *method; + char *log_filepath; + char *pid_filepath; +#ifdef CONFIG_FSFREEZE + char *fsfreeze_hook; +#endif + char *state_dir; +#ifdef _WIN32 + const char *service; +#endif + gchar *bliststr; /* blockedrpcs may point to this string */ + gchar *aliststr; /* allowedrpcs may point to this string */ + GList *blockedrpcs; + GList *allowedrpcs; + int daemonize; + GLogLevelFlags log_level; + int dumpconf; + bool retry_path; +}; + struct GAState { JSONMessageParser parser; GMainLoop *main_loop; @@ -226,12 +248,16 @@ static void usage(const char *cmd) #ifdef CONFIG_FSFREEZE g_autofree char *fsfreeze_hook = get_relocated_path(QGA_FSFREEZE_HOOK_DEFAULT); #endif + g_autofree char *conf_path = get_relocated_path(QGA_CONF_DEFAULT); printf( "Usage: %s [-m <method> -p <path>] [<options>]\n" "QEMU Guest Agent " QEMU_FULL_VERSION "\n" QEMU_COPYRIGHT "\n" "\n" +" -c, --config=PATH configuration file path (default is\n" +" %s/qemu-ga.conf\n" +" unless overriden by the QGA_CONF environment variable)\n" " -m, --method transport method: one of unix-listen, virtio-serial,\n" " isa-serial, or vsock-listen (virtio-serial is the default)\n" " -p, --path device/socket path (the default for virtio-serial is:\n" @@ -272,8 +298,8 @@ QEMU_COPYRIGHT "\n" " plug/unplug, etc.)\n" " -h, --help display this help and exit\n" "\n" -QEMU_HELP_BOTTOM "\n" - , cmd, QGA_VIRTIO_PATH_DEFAULT, QGA_SERIAL_PATH_DEFAULT, +QEMU_HELP_BOTTOM "\n", + cmd, conf_path, QGA_VIRTIO_PATH_DEFAULT, QGA_SERIAL_PATH_DEFAULT, dfl_pathnames.pidfile, #ifdef CONFIG_FSFREEZE fsfreeze_hook, @@ -397,60 +423,79 @@ static gint ga_strcmp(gconstpointer str1, gconstpointer str2) return strcmp(str1, str2); } -/* disable commands that aren't safe for fsfreeze */ -static void ga_disable_not_allowed_freeze(const QmpCommand *cmd, void *opaque) +static bool ga_command_is_allowed(const QmpCommand *cmd, GAState *state) { - bool allowed = false; int i = 0; + GAConfig *config = state->config; const char *name = qmp_command_name(cmd); + /* Fallback policy is allow everything */ + bool allowed = true; + + if (config->allowedrpcs) { + /* + * If an allow-list is given, this changes the fallback + * policy to deny everything + */ + allowed = false; - while (ga_freeze_allowlist[i] != NULL) { - if (strcmp(name, ga_freeze_allowlist[i]) == 0) { + if (g_list_find_custom(config->allowedrpcs, name, ga_strcmp) != NULL) { allowed = true; } - i++; } - if (!allowed) { - g_debug("disabling command: %s", name); - qmp_disable_command(&ga_commands, name, "the agent is in frozen state"); - } -} -/* [re-]enable all commands, except those explicitly blocked by user */ -static void ga_enable_non_blocked(const QmpCommand *cmd, void *opaque) -{ - GAState *s = opaque; - GList *blockedrpcs = s->blockedrpcs; - GList *allowedrpcs = s->allowedrpcs; - const char *name = qmp_command_name(cmd); - - if (g_list_find_custom(blockedrpcs, name, ga_strcmp) == NULL) { - if (qmp_command_is_enabled(cmd)) { - return; + /* + * If both allowedrpcs and blockedrpcs are set, the blocked + * list will take priority + */ + if (config->blockedrpcs) { + if (g_list_find_custom(config->blockedrpcs, name, ga_strcmp) != NULL) { + allowed = false; } + } - if (allowedrpcs && - g_list_find_custom(allowedrpcs, name, ga_strcmp) == NULL) { - return; - } + /* + * If frozen, this filtering must take priority over + * absolutely everything + */ + if (state->frozen) { + allowed = false; - g_debug("enabling command: %s", name); - qmp_enable_command(&ga_commands, name); + while (ga_freeze_allowlist[i] != NULL) { + if (strcmp(name, ga_freeze_allowlist[i]) == 0) { + allowed = true; + } + i++; + } } + + return allowed; } -/* disable commands that aren't allowed */ -static void ga_disable_not_allowed(const QmpCommand *cmd, void *opaque) +static void ga_apply_command_filters_iter(const QmpCommand *cmd, void *opaque) { - GList *allowedrpcs = opaque; + GAState *state = opaque; + bool want = ga_command_is_allowed(cmd, state); + bool have = qmp_command_is_enabled(cmd); const char *name = qmp_command_name(cmd); - if (g_list_find_custom(allowedrpcs, name, ga_strcmp) == NULL) { + if (want == have) { + return; + } + + if (have) { g_debug("disabling command: %s", name); qmp_disable_command(&ga_commands, name, "the command is not allowed"); + } else { + g_debug("enabling command: %s", name); + qmp_enable_command(&ga_commands, name); } } +static void ga_apply_command_filters(GAState *state) +{ + qmp_for_each_command(&ga_commands, ga_apply_command_filters_iter, state); +} + static bool ga_create_file(const char *path) { int fd = open(path, O_CREAT | O_WRONLY, S_IWUSR | S_IRUSR); @@ -483,15 +528,14 @@ void ga_set_frozen(GAState *s) if (ga_is_frozen(s)) { return; } - /* disable all forbidden (for frozen state) commands */ - qmp_for_each_command(&ga_commands, ga_disable_not_allowed_freeze, NULL); g_warning("disabling logging due to filesystem freeze"); - ga_disable_logging(s); s->frozen = true; if (!ga_create_file(s->state_filepath_isfrozen)) { g_warning("unable to create %s, fsfreeze may not function properly", s->state_filepath_isfrozen); } + ga_apply_command_filters(s); + ga_disable_logging(s); } void ga_unset_frozen(GAState *s) @@ -523,12 +567,12 @@ void ga_unset_frozen(GAState *s) } /* enable all disabled, non-blocked and allowed commands */ - qmp_for_each_command(&ga_commands, ga_enable_non_blocked, s); s->frozen = false; if (!ga_delete_file(s->state_filepath_isfrozen)) { g_warning("unable to delete %s, fsfreeze may not function properly", s->state_filepath_isfrozen); } + ga_apply_command_filters(s); } #ifdef CONFIG_FSFREEZE @@ -996,38 +1040,14 @@ static GList *split_list(const gchar *str, const gchar *delim) return list; } -struct GAConfig { - char *channel_path; - char *method; - char *log_filepath; - char *pid_filepath; -#ifdef CONFIG_FSFREEZE - char *fsfreeze_hook; -#endif - char *state_dir; -#ifdef _WIN32 - const char *service; -#endif - gchar *bliststr; /* blockedrpcs may point to this string */ - gchar *aliststr; /* allowedrpcs may point to this string */ - GList *blockedrpcs; - GList *allowedrpcs; - int daemonize; - GLogLevelFlags log_level; - int dumpconf; - bool retry_path; -}; - -static void config_load(GAConfig *config) +static void config_load(GAConfig *config, const char *confpath, bool required) { GError *gerr = NULL; GKeyFile *keyfile; - g_autofree char *conf = g_strdup(g_getenv("QGA_CONF")) ?: get_relocated_path(QGA_CONF_DEFAULT); - const gchar *blockrpcs_key = "block-rpcs"; /* read system config */ keyfile = g_key_file_new(); - if (!g_key_file_load_from_file(keyfile, conf, 0, &gerr)) { + if (!g_key_file_load_from_file(keyfile, confpath, 0, &gerr)) { goto end; } if (g_key_file_has_key(keyfile, "general", "daemon", NULL)) { @@ -1071,9 +1091,9 @@ static void config_load(GAConfig *config) g_key_file_get_boolean(keyfile, "general", "retry-path", &gerr); } - if (g_key_file_has_key(keyfile, "general", blockrpcs_key, NULL)) { + if (g_key_file_has_key(keyfile, "general", "block-rpcs", NULL)) { config->bliststr = - g_key_file_get_string(keyfile, "general", blockrpcs_key, &gerr); + g_key_file_get_string(keyfile, "general", "block-rpcs", &gerr); config->blockedrpcs = g_list_concat(config->blockedrpcs, split_list(config->bliststr, ",")); } @@ -1084,19 +1104,12 @@ static void config_load(GAConfig *config) split_list(config->aliststr, ",")); } - if (g_key_file_has_key(keyfile, "general", blockrpcs_key, NULL) && - g_key_file_has_key(keyfile, "general", "allow-rpcs", NULL)) { - g_critical("wrong config, using 'block-rpcs' and 'allow-rpcs' keys at" - " the same time is not allowed"); - exit(EXIT_FAILURE); - } - end: g_key_file_free(keyfile); - if (gerr && - !(gerr->domain == G_FILE_ERROR && gerr->code == G_FILE_ERROR_NOENT)) { + if (gerr && (required || + !(gerr->domain == G_FILE_ERROR && gerr->code == G_FILE_ERROR_NOENT))) { g_critical("error loading configuration from path: %s, %s", - conf, gerr->message); + confpath, gerr->message); exit(EXIT_FAILURE); } g_clear_error(&gerr); @@ -1168,12 +1181,12 @@ static void config_dump(GAConfig *config) static void config_parse(GAConfig *config, int argc, char **argv) { - const char *sopt = "hVvdm:p:l:f:F::b:a:s:t:Dr"; + const char *sopt = "hVvdc:m:p:l:f:F::b:a:s:t:Dr"; int opt_ind = 0, ch; - bool block_rpcs = false, allow_rpcs = false; const struct option lopt[] = { { "help", 0, NULL, 'h' }, { "version", 0, NULL, 'V' }, + { "config", 1, NULL, 'c' }, { "dump-conf", 0, NULL, 'D' }, { "logfile", 1, NULL, 'l' }, { "pidfile", 1, NULL, 'f' }, @@ -1193,6 +1206,26 @@ static void config_parse(GAConfig *config, int argc, char **argv) { "retry-path", 0, NULL, 'r' }, { NULL, 0, NULL, 0 } }; + g_autofree char *confpath = g_strdup(g_getenv("QGA_CONF")) ?: + get_relocated_path(QGA_CONF_DEFAULT); + bool confrequired = false; + + while ((ch = getopt_long(argc, argv, sopt, lopt, NULL)) != -1) { + switch (ch) { + case 'c': + g_free(confpath); + confpath = g_strdup(optarg); + confrequired = true; + break; + default: + break; + } + } + + config_load(config, confpath, confrequired); + + /* Reset for second pass */ + optind = 1; while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) { switch (ch) { @@ -1245,7 +1278,6 @@ static void config_parse(GAConfig *config, int argc, char **argv) } config->blockedrpcs = g_list_concat(config->blockedrpcs, split_list(optarg, ",")); - block_rpcs = true; break; } case 'a': { @@ -1255,7 +1287,6 @@ static void config_parse(GAConfig *config, int argc, char **argv) } config->allowedrpcs = g_list_concat(config->allowedrpcs, split_list(optarg, ",")); - allow_rpcs = true; break; } #ifdef _WIN32 @@ -1296,12 +1327,6 @@ static void config_parse(GAConfig *config, int argc, char **argv) exit(EXIT_FAILURE); } } - - if (block_rpcs && allow_rpcs) { - g_critical("wrong commandline, using --block-rpcs and --allow-rpcs at the" - " same time is not allowed"); - exit(EXIT_FAILURE); - } } static void config_free(GAConfig *config) @@ -1395,6 +1420,10 @@ static GAState *initialize_agent(GAConfig *config, int socket_activation) " '%s': %s", config->state_dir, strerror(errno)); return NULL; } + + if (!vss_init(true)) { + g_debug("vss_init failed, vss commands will not function"); + } #endif if (ga_is_frozen(s)) { @@ -1408,7 +1437,6 @@ static GAState *initialize_agent(GAConfig *config, int socket_activation) s->deferred_options.log_filepath = config->log_filepath; } ga_disable_logging(s); - qmp_for_each_command(&ga_commands, ga_disable_not_allowed_freeze, NULL); } else { if (config->daemonize) { become_daemon(config->pid_filepath); @@ -1432,25 +1460,6 @@ static GAState *initialize_agent(GAConfig *config, int socket_activation) return NULL; } - if (config->allowedrpcs) { - qmp_for_each_command(&ga_commands, ga_disable_not_allowed, config->allowedrpcs); - s->allowedrpcs = config->allowedrpcs; - } - - /* - * Some commands can be blocked due to system limitation. - * Initialize blockedrpcs list even if allowedrpcs specified. - */ - config->blockedrpcs = ga_command_init_blockedrpcs(config->blockedrpcs); - if (config->blockedrpcs) { - GList *l = config->blockedrpcs; - s->blockedrpcs = config->blockedrpcs; - do { - g_debug("disabling command: %s", (char *)l->data); - qmp_disable_command(&ga_commands, l->data, NULL); - l = g_list_next(l); - } while (l); - } s->command_state = ga_command_state_new(); ga_command_state_init(s, s->command_state); ga_command_state_init_all(s->command_state); @@ -1476,6 +1485,8 @@ static GAState *initialize_agent(GAConfig *config, int socket_activation) } #endif + ga_apply_command_filters(s); + ga_state = s; return s; } @@ -1579,7 +1590,6 @@ int main(int argc, char **argv) qga_qmp_init_marshal(&ga_commands); init_dfl_pathnames(); - config_load(config); config_parse(config, argc, argv); if (config->pid_filepath == NULL) { diff --git a/qga/qapi-schema.json b/qga/qapi-schema.json index 1273d85bb5..495706cf73 100644 --- a/qga/qapi-schema.json +++ b/qga/qapi-schema.json @@ -412,7 +412,8 @@ # Since: 0.15.0 ## { 'enum': 'GuestFsfreezeStatus', - 'data': [ 'thawed', 'frozen' ] } + 'data': [ 'thawed', 'frozen' ], + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSFREEZE'] } } ## # @guest-fsfreeze-status: @@ -429,7 +430,8 @@ # Since: 0.15.0 ## { 'command': 'guest-fsfreeze-status', - 'returns': 'GuestFsfreezeStatus' } + 'returns': 'GuestFsfreezeStatus', + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSFREEZE'] } } ## # @guest-fsfreeze-freeze: @@ -451,7 +453,8 @@ # Since: 0.15.0 ## { 'command': 'guest-fsfreeze-freeze', - 'returns': 'int' } + 'returns': 'int', + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSFREEZE'] } } ## # @guest-fsfreeze-freeze-list: @@ -471,7 +474,8 @@ ## { 'command': 'guest-fsfreeze-freeze-list', 'data': { '*mountpoints': ['str'] }, - 'returns': 'int' } + 'returns': 'int', + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSFREEZE'] } } ## # @guest-fsfreeze-thaw: @@ -488,7 +492,8 @@ # Since: 0.15.0 ## { 'command': 'guest-fsfreeze-thaw', - 'returns': 'int' } + 'returns': 'int', + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSFREEZE'] } } ## # @GuestFilesystemTrimResult: @@ -505,7 +510,8 @@ ## { 'struct': 'GuestFilesystemTrimResult', 'data': {'path': 'str', - '*trimmed': 'int', '*minimum': 'int', '*error': 'str'} } + '*trimmed': 'int', '*minimum': 'int', '*error': 'str'}, + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSTRIM'] } } ## # @GuestFilesystemTrimResponse: @@ -515,7 +521,8 @@ # Since: 2.4 ## { 'struct': 'GuestFilesystemTrimResponse', - 'data': {'paths': ['GuestFilesystemTrimResult']} } + 'data': {'paths': ['GuestFilesystemTrimResult']}, + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSTRIM'] } } ## # @guest-fstrim: @@ -537,7 +544,8 @@ ## { 'command': 'guest-fstrim', 'data': { '*minimum': 'int' }, - 'returns': 'GuestFilesystemTrimResponse' } + 'returns': 'GuestFilesystemTrimResponse', + 'if': { 'any': ['CONFIG_WIN32', 'CONFIG_FSTRIM'] } } ## # @guest-suspend-disk: @@ -566,7 +574,8 @@ # # Since: 1.1 ## -{ 'command': 'guest-suspend-disk', 'success-response': false } +{ 'command': 'guest-suspend-disk', 'success-response': false, + 'if': { 'any': ['CONFIG_LINUX', 'CONFIG_WIN32'] } } ## # @guest-suspend-ram: @@ -602,7 +611,8 @@ # # Since: 1.1 ## -{ 'command': 'guest-suspend-ram', 'success-response': false } +{ 'command': 'guest-suspend-ram', 'success-response': false, + 'if': { 'any': ['CONFIG_LINUX', 'CONFIG_WIN32'] } } ## # @guest-suspend-hybrid: @@ -637,7 +647,8 @@ # # Since: 1.1 ## -{ 'command': 'guest-suspend-hybrid', 'success-response': false } +{ 'command': 'guest-suspend-hybrid', 'success-response': false, + 'if': 'CONFIG_LINUX' } ## # @GuestIpAddressType: @@ -651,7 +662,8 @@ # Since: 1.1 ## { 'enum': 'GuestIpAddressType', - 'data': [ 'ipv4', 'ipv6' ] } + 'data': [ 'ipv4', 'ipv6' ], + 'if': { 'any': ['CONFIG_WIN32', 'HAVE_GETIFADDRS'] } } ## # @GuestIpAddress: @@ -667,7 +679,8 @@ { 'struct': 'GuestIpAddress', 'data': {'ip-address': 'str', 'ip-address-type': 'GuestIpAddressType', - 'prefix': 'int'} } + 'prefix': 'int'}, + 'if': { 'any': ['CONFIG_WIN32', 'HAVE_GETIFADDRS'] } } ## # @GuestNetworkInterfaceStat: @@ -699,7 +712,8 @@ 'tx-packets': 'uint64', 'tx-errs': 'uint64', 'tx-dropped': 'uint64' - } } + }, + 'if': { 'any': ['CONFIG_WIN32', 'HAVE_GETIFADDRS'] } } ## # @GuestNetworkInterface: @@ -719,7 +733,8 @@ 'data': {'name': 'str', '*hardware-address': 'str', '*ip-addresses': ['GuestIpAddress'], - '*statistics': 'GuestNetworkInterfaceStat' } } + '*statistics': 'GuestNetworkInterfaceStat' }, + 'if': { 'any': ['CONFIG_WIN32', 'HAVE_GETIFADDRS'] } } ## # @guest-network-get-interfaces: @@ -731,7 +746,8 @@ # Since: 1.1 ## { 'command': 'guest-network-get-interfaces', - 'returns': ['GuestNetworkInterface'] } + 'returns': ['GuestNetworkInterface'], + 'if': { 'any': ['CONFIG_WIN32', 'HAVE_GETIFADDRS'] } } ## # @GuestLogicalProcessor: @@ -750,7 +766,8 @@ { 'struct': 'GuestLogicalProcessor', 'data': {'logical-id': 'int', 'online': 'bool', - '*can-offline': 'bool'} } + '*can-offline': 'bool'}, + 'if': { 'any': ['CONFIG_LINUX', 'CONFIG_WIN32'] } } ## # @guest-get-vcpus: @@ -765,7 +782,8 @@ # Since: 1.5 ## { 'command': 'guest-get-vcpus', - 'returns': ['GuestLogicalProcessor'] } + 'returns': ['GuestLogicalProcessor'], + 'if': { 'any': ['CONFIG_LINUX', 'CONFIG_WIN32'] } } ## # @guest-set-vcpus: @@ -807,7 +825,8 @@ ## { 'command': 'guest-set-vcpus', 'data': {'vcpus': ['GuestLogicalProcessor'] }, - 'returns': 'int' } + 'returns': 'int', + 'if': 'CONFIG_LINUX' } ## # @GuestDiskBusType: @@ -859,7 +878,8 @@ { 'enum': 'GuestDiskBusType', 'data': [ 'ide', 'fdc', 'scsi', 'virtio', 'xen', 'usb', 'uml', 'sata', 'sd', 'unknown', 'ieee1394', 'ssa', 'fibre', 'raid', 'iscsi', - 'sas', 'mmc', 'virtual', 'file-backed-virtual', 'nvme' ] } + 'sas', 'mmc', 'virtual', 'file-backed-virtual', 'nvme' ], + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LINUX' ] } } ## @@ -877,7 +897,8 @@ ## { 'struct': 'GuestPCIAddress', 'data': {'domain': 'int', 'bus': 'int', - 'slot': 'int', 'function': 'int'} } + 'slot': 'int', 'function': 'int'}, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LINUX' ] } } ## # @GuestCCWAddress: @@ -896,7 +917,8 @@ 'data': {'cssid': 'int', 'ssid': 'int', 'subchno': 'int', - 'devno': 'int'} } + 'devno': 'int'}, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LINUX' ] } } ## # @GuestDiskAddress: @@ -925,7 +947,8 @@ 'bus-type': 'GuestDiskBusType', 'bus': 'int', 'target': 'int', 'unit': 'int', '*serial': 'str', '*dev': 'str', - '*ccw-address': 'GuestCCWAddress'} } + '*ccw-address': 'GuestCCWAddress'}, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LINUX' ] } } ## # @GuestNVMeSmart: @@ -962,7 +985,8 @@ 'media-errors-lo': 'uint64', 'media-errors-hi': 'uint64', 'number-of-error-log-entries-lo': 'uint64', - 'number-of-error-log-entries-hi': 'uint64' } } + 'number-of-error-log-entries-hi': 'uint64' }, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LIBUDEV' ] } } ## # @GuestDiskSmart: @@ -976,7 +1000,8 @@ { 'union': 'GuestDiskSmart', 'base': { 'type': 'GuestDiskBusType' }, 'discriminator': 'type', - 'data': { 'nvme': 'GuestNVMeSmart' } } + 'data': { 'nvme': 'GuestNVMeSmart' }, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LIBUDEV' ] } } ## # @GuestDiskInfo: @@ -1001,7 +1026,8 @@ { 'struct': 'GuestDiskInfo', 'data': {'name': 'str', 'partition': 'bool', '*dependencies': ['str'], '*address': 'GuestDiskAddress', '*alias': 'str', - '*smart': 'GuestDiskSmart'} } + '*smart': 'GuestDiskSmart'}, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LIBUDEV' ] } } ## # @guest-get-disks: @@ -1014,7 +1040,8 @@ # Since: 5.2 ## { 'command': 'guest-get-disks', - 'returns': ['GuestDiskInfo'] } + 'returns': ['GuestDiskInfo'], + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LIBUDEV' ] } } ## # @GuestFilesystemInfo: @@ -1040,7 +1067,8 @@ { 'struct': 'GuestFilesystemInfo', 'data': {'name': 'str', 'mountpoint': 'str', 'type': 'str', '*used-bytes': 'uint64', '*total-bytes': 'uint64', - '*total-bytes-privileged': 'uint64', 'disk': ['GuestDiskAddress']} } + '*total-bytes-privileged': 'uint64', 'disk': ['GuestDiskAddress']}, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LINUX' ] } } ## # @guest-get-fsinfo: @@ -1053,7 +1081,8 @@ # Since: 2.2 ## { 'command': 'guest-get-fsinfo', - 'returns': ['GuestFilesystemInfo'] } + 'returns': ['GuestFilesystemInfo'], + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LINUX' ] } } ## # @guest-set-user-password: @@ -1080,7 +1109,8 @@ # Since: 2.3 ## { 'command': 'guest-set-user-password', - 'data': { 'username': 'str', 'password': 'str', 'crypted': 'bool' } } + 'data': { 'username': 'str', 'password': 'str', 'crypted': 'bool' }, + 'if': { 'any': [ 'CONFIG_WIN32', 'CONFIG_LINUX', 'CONFIG_FREEBSD'] } } ## # @GuestMemoryBlock: @@ -1100,7 +1130,8 @@ { 'struct': 'GuestMemoryBlock', 'data': {'phys-index': 'uint64', 'online': 'bool', - '*can-offline': 'bool'} } + '*can-offline': 'bool'}, + 'if': 'CONFIG_LINUX' } ## # @guest-get-memory-blocks: @@ -1116,7 +1147,8 @@ # Since: 2.3 ## { 'command': 'guest-get-memory-blocks', - 'returns': ['GuestMemoryBlock'] } + 'returns': ['GuestMemoryBlock'], + 'if': 'CONFIG_LINUX' } ## # @GuestMemoryBlockResponseType: @@ -1139,7 +1171,8 @@ ## { 'enum': 'GuestMemoryBlockResponseType', 'data': ['success', 'not-found', 'operation-not-supported', - 'operation-failed'] } + 'operation-failed'], + 'if': 'CONFIG_LINUX' } ## # @GuestMemoryBlockResponse: @@ -1157,7 +1190,8 @@ { 'struct': 'GuestMemoryBlockResponse', 'data': { 'phys-index': 'uint64', 'response': 'GuestMemoryBlockResponseType', - '*error-code': 'int' }} + '*error-code': 'int' }, + 'if': 'CONFIG_LINUX'} ## # @guest-set-memory-blocks: @@ -1188,7 +1222,8 @@ ## { 'command': 'guest-set-memory-blocks', 'data': {'mem-blks': ['GuestMemoryBlock'] }, - 'returns': ['GuestMemoryBlockResponse'] } + 'returns': ['GuestMemoryBlockResponse'], + 'if': 'CONFIG_LINUX' } ## # @GuestMemoryBlockInfo: @@ -1200,7 +1235,8 @@ # Since: 2.3 ## { 'struct': 'GuestMemoryBlockInfo', - 'data': {'size': 'uint64'} } + 'data': {'size': 'uint64'}, + 'if': 'CONFIG_LINUX' } ## # @guest-get-memory-block-info: @@ -1212,7 +1248,8 @@ # Since: 2.3 ## { 'command': 'guest-get-memory-block-info', - 'returns': 'GuestMemoryBlockInfo' } + 'returns': 'GuestMemoryBlockInfo', + 'if': 'CONFIG_LINUX' } ## # @GuestExecStatus: @@ -1378,7 +1415,8 @@ # Since: 2.10 ## { 'struct': 'GuestUser', - 'data': { 'user': 'str', 'login-time': 'number', '*domain': 'str' } } + 'data': { 'user': 'str', 'login-time': 'number', '*domain': 'str' }, + 'if': { 'any': ['CONFIG_WIN32', 'HAVE_UTMPX' ] } } ## # @guest-get-users: @@ -1390,7 +1428,8 @@ # Since: 2.10 ## { 'command': 'guest-get-users', - 'returns': ['GuestUser'] } + 'returns': ['GuestUser'], + 'if': { 'any': ['CONFIG_WIN32', 'HAVE_UTMPX' ] } } ## # @GuestTimezone: @@ -1499,7 +1538,8 @@ # @pci: PCI device ## { 'enum': 'GuestDeviceType', - 'data': [ 'pci' ] } + 'data': [ 'pci' ], + 'if': 'CONFIG_WIN32' } ## # @GuestDeviceIdPCI: @@ -1511,7 +1551,8 @@ # Since: 5.2 ## { 'struct': 'GuestDeviceIdPCI', - 'data': { 'vendor-id': 'uint16', 'device-id': 'uint16' } } + 'data': { 'vendor-id': 'uint16', 'device-id': 'uint16' }, + 'if': 'CONFIG_WIN32' } ## # @GuestDeviceId: @@ -1525,7 +1566,8 @@ { 'union': 'GuestDeviceId', 'base': { 'type': 'GuestDeviceType' }, 'discriminator': 'type', - 'data': { 'pci': 'GuestDeviceIdPCI' } } + 'data': { 'pci': 'GuestDeviceIdPCI' }, + 'if': 'CONFIG_WIN32' } ## # @GuestDeviceInfo: @@ -1546,7 +1588,8 @@ '*driver-date': 'int', '*driver-version': 'str', '*id': 'GuestDeviceId' - } } + }, + 'if': 'CONFIG_WIN32' } ## # @guest-get-devices: @@ -1558,7 +1601,8 @@ # Since: 5.2 ## { 'command': 'guest-get-devices', - 'returns': ['GuestDeviceInfo'] } + 'returns': ['GuestDeviceInfo'], + 'if': 'CONFIG_WIN32' } ## # @GuestAuthorizedKeys: @@ -1685,7 +1729,8 @@ '*ios-pgr': 'uint64', '*total-ticks': 'uint64', '*weight-ticks': 'uint64' - } } + }, + 'if': 'CONFIG_LINUX' } ## # @GuestDiskStatsInfo: @@ -1702,7 +1747,8 @@ 'data': {'name': 'str', 'major': 'uint64', 'minor': 'uint64', - 'stats': 'GuestDiskStats' } } + 'stats': 'GuestDiskStats' }, + 'if': 'CONFIG_LINUX' } ## # @guest-get-diskstats: @@ -1714,7 +1760,8 @@ # Since: 7.1 ## { 'command': 'guest-get-diskstats', - 'returns': ['GuestDiskStatsInfo'] + 'returns': ['GuestDiskStatsInfo'], + 'if': 'CONFIG_LINUX' } ## @@ -1727,7 +1774,8 @@ # Since: 7.1 ## { 'enum': 'GuestCpuStatsType', - 'data': [ 'linux' ] } + 'data': [ 'linux' ], + 'if': 'CONFIG_LINUX' } ## @@ -1772,7 +1820,8 @@ '*steal': 'uint64', '*guest': 'uint64', '*guestnice': 'uint64' - } } + }, + 'if': 'CONFIG_LINUX' } ## # @GuestCpuStats: @@ -1786,7 +1835,8 @@ { 'union': 'GuestCpuStats', 'base': { 'type': 'GuestCpuStatsType' }, 'discriminator': 'type', - 'data': { 'linux': 'GuestLinuxCpuStats' } } + 'data': { 'linux': 'GuestLinuxCpuStats' }, + 'if': 'CONFIG_LINUX' } ## # @guest-get-cpustats: @@ -1798,5 +1848,79 @@ # Since: 7.1 ## { 'command': 'guest-get-cpustats', - 'returns': ['GuestCpuStats'] + 'returns': ['GuestCpuStats'], + 'if': 'CONFIG_LINUX' +} + +## +# @GuestNetworkRoute: +# +# Route information, currently, only linux supported. +# +# @iface: The destination network or host's egress network interface in the routing table +# +# @destination: The IP address of the target network or host, The final destination of the packet +# +# @metric: Route metric +# +# @gateway: The IP address of the next hop router +# +# @mask: Subnet Mask (IPv4 only) +# +# @irtt: Initial round-trip delay (not for windows, IPv4 only) +# +# @flags: Route flags (not for windows) +# +# @refcnt: The route's reference count (not for windows) +# +# @use: Route usage count (not for windows) +# +# @window: TCP window size, used for flow control (not for windows, IPv4 only) +# +# @mtu: Data link layer maximum packet size (not for windows) +# +# @desprefixlen: Destination prefix length (for IPv6) +# +# @source: Source IP address (for IPv6) +# +# @srcprefixlen: Source prefix length (for IPv6) +# +# @nexthop: Next hop IP address (for IPv6) +# +# @version: IP version (4 or 6) +# +# Since: 9.1 + +## +{ 'struct': 'GuestNetworkRoute', + 'data': {'iface': 'str', + 'destination': 'str', + 'metric': 'int', + '*gateway': 'str', + '*mask': 'str', + '*irtt': 'int', + '*flags': 'uint64', + '*refcnt': 'int', + '*use': 'int', + '*window': 'int', + '*mtu': 'int', + '*desprefixlen': 'str', + '*source': 'str', + '*srcprefixlen': 'str', + '*nexthop': 'str', + 'version': 'int' + }, + 'if': 'CONFIG_LINUX' } + +## +# @guest-network-get-route: +# +# Retrieve information about route of network. +# Returns: List of route info of guest. +# +# Since: 9.1 +## +{ 'command': 'guest-network-get-route', + 'returns': ['GuestNetworkRoute'], + 'if': 'CONFIG_LINUX' } diff --git a/semihosting/Kconfig b/semihosting/Kconfig index eaf3a20ef5..fbe6ac87f9 100644 --- a/semihosting/Kconfig +++ b/semihosting/Kconfig @@ -1,6 +1,7 @@ config SEMIHOSTING bool + depends on TCG config ARM_COMPATIBLE_SEMIHOSTING bool diff --git a/system/physmem.c b/system/physmem.c index 9a3b3a7636..0e19186e1b 100644 --- a/system/physmem.c +++ b/system/physmem.c @@ -763,6 +763,7 @@ void cpu_address_space_init(CPUState *cpu, int asidx, if (!cpu->cpu_ases) { cpu->cpu_ases = g_new0(CPUAddressSpace, cpu->num_ases); + cpu->cpu_ases_count = cpu->num_ases; } newas = &cpu->cpu_ases[asidx]; @@ -776,6 +777,34 @@ void cpu_address_space_init(CPUState *cpu, int asidx, } } +void cpu_address_space_destroy(CPUState *cpu, int asidx) +{ + CPUAddressSpace *cpuas; + + assert(cpu->cpu_ases); + assert(asidx >= 0 && asidx < cpu->num_ases); + /* KVM cannot currently support multiple address spaces. */ + assert(asidx == 0 || !kvm_enabled()); + + cpuas = &cpu->cpu_ases[asidx]; + if (tcg_enabled()) { + memory_listener_unregister(&cpuas->tcg_as_listener); + } + + address_space_destroy(cpuas->as); + g_free_rcu(cpuas->as, rcu); + + if (asidx == 0) { + /* reset the convenience alias for address space 0 */ + cpu->as = NULL; + } + + if (--cpu->cpu_ases_count == 0) { + g_free(cpu->cpu_ases); + cpu->cpu_ases = NULL; + } +} + AddressSpace *cpu_get_address_space(CPUState *cpu, int asidx) { /* Return the AddressSpace corresponding to the specified index */ diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index c3a9b5eb1e..554b8736bb 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -477,11 +477,9 @@ static GDBFeature *arm_gen_dynamic_m_secextreg_feature(CPUState *cs, void arm_cpu_register_gdb_commands(ARMCPU *cpu) { - GArray *query_table = - g_array_new(FALSE, FALSE, sizeof(GdbCmdParseEntry)); - GArray *set_table = - g_array_new(FALSE, FALSE, sizeof(GdbCmdParseEntry)); - GString *qsupported_features = g_string_new(NULL); + g_autoptr(GPtrArray) query_table = g_ptr_array_new(); + g_autoptr(GPtrArray) set_table = g_ptr_array_new(); + g_autoptr(GString) qsupported_features = g_string_new(NULL); if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { #ifdef TARGET_AARCH64 @@ -492,16 +490,12 @@ void arm_cpu_register_gdb_commands(ARMCPU *cpu) /* Set arch-specific handlers for 'q' commands. */ if (query_table->len) { - gdb_extend_query_table(&g_array_index(query_table, - GdbCmdParseEntry, 0), - query_table->len); + gdb_extend_query_table(query_table); } /* Set arch-specific handlers for 'Q' commands. */ if (set_table->len) { - gdb_extend_set_table(&g_array_index(set_table, - GdbCmdParseEntry, 0), - set_table->len); + gdb_extend_set_table(set_table); } /* Set arch-specific qSupported feature. */ diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index 2e2bc2700b..c8cef8cbc0 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -564,7 +564,7 @@ enum Command { NUM_CMDS }; -static GdbCmdParseEntry cmd_handler_table[NUM_CMDS] = { +static const GdbCmdParseEntry cmd_handler_table[NUM_CMDS] = { [qMemTags] = { .handler = handle_q_memtag, .cmd_startswith = true, @@ -590,17 +590,16 @@ static GdbCmdParseEntry cmd_handler_table[NUM_CMDS] = { #endif /* CONFIG_USER_ONLY */ void aarch64_cpu_register_gdb_commands(ARMCPU *cpu, GString *qsupported, - GArray *qtable, GArray *stable) + GPtrArray *qtable, GPtrArray *stable) { #ifdef CONFIG_USER_ONLY /* MTE */ if (cpu_isar_feature(aa64_mte, cpu)) { g_string_append(qsupported, ";memory-tagging+"); - g_array_append_val(qtable, cmd_handler_table[qMemTags]); - g_array_append_val(qtable, cmd_handler_table[qIsAddressTagged]); - - g_array_append_val(stable, cmd_handler_table[QMemTags]); + g_ptr_array_add(qtable, (gpointer) &cmd_handler_table[qMemTags]); + g_ptr_array_add(qtable, (gpointer) &cmd_handler_table[qIsAddressTagged]); + g_ptr_array_add(stable, (gpointer) &cmd_handler_table[QMemTags]); } #endif } diff --git a/target/arm/internals.h b/target/arm/internals.h index da22d04121..757b1fae92 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -359,8 +359,8 @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu); void arm_translate_init(void); void arm_cpu_register_gdb_commands(ARMCPU *cpu); -void aarch64_cpu_register_gdb_commands(ARMCPU *cpu, GString *, GArray *, - GArray *); +void aarch64_cpu_register_gdb_commands(ARMCPU *cpu, GString *, + GPtrArray *, GPtrArray *); void arm_restore_state_to_opc(CPUState *cs, const TranslationBlock *tb, diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index 0ea8668ab4..c60d2a7ec9 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -928,6 +928,8 @@ uint32_t HELPER(sqrt_f16)(uint32_t a, void *fpstp) void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) { + uintptr_t ra = GETPC(); + /* * Implement DC ZVA, which zeroes a fixed-length block of memory. * Note that we do not implement the (architecturally mandated) @@ -948,8 +950,6 @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) #ifndef CONFIG_USER_ONLY if (unlikely(!mem)) { - uintptr_t ra = GETPC(); - /* * Trap if accessing an invalid page. DC_ZVA requires that we supply * the original pointer for an invalid page. But watchpoints require @@ -971,7 +971,9 @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) } #endif + set_helper_retaddr(ra); memset(mem, 0, blocklen); + clear_helper_retaddr(); } void HELPER(unaligned_access)(CPUARMState *env, uint64_t addr, @@ -1120,7 +1122,9 @@ static uint64_t set_step(CPUARMState *env, uint64_t toaddr, } #endif /* Easy case: just memset the host memory */ + set_helper_retaddr(ra); memset(mem, data, setsize); + clear_helper_retaddr(); return setsize; } @@ -1163,7 +1167,9 @@ static uint64_t set_step_tags(CPUARMState *env, uint64_t toaddr, } #endif /* Easy case: just memset the host memory */ + set_helper_retaddr(ra); memset(mem, data, setsize); + clear_helper_retaddr(); mte_mops_set_tags(env, toaddr, setsize, *mtedesc); return setsize; } @@ -1497,7 +1503,9 @@ static uint64_t copy_step(CPUARMState *env, uint64_t toaddr, uint64_t fromaddr, } #endif /* Easy case: just memmove the host memory */ + set_helper_retaddr(ra); memmove(wmem, rmem, copysize); + clear_helper_retaddr(); return copysize; } @@ -1572,7 +1580,9 @@ static uint64_t copy_step_rev(CPUARMState *env, uint64_t toaddr, * Easy case: just memmove the host memory. Note that wmem and * rmem here point to the *last* byte to copy. */ + set_helper_retaddr(ra); memmove(wmem - (copysize - 1), rmem - (copysize - 1), copysize); + clear_helper_retaddr(); return copysize; } diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c index 5a6dd76489..50bb088d04 100644 --- a/target/arm/tcg/sme_helper.c +++ b/target/arm/tcg/sme_helper.c @@ -517,6 +517,8 @@ void sme_ld1(CPUARMState *env, void *za, uint64_t *vg, clr_fn(za, 0, reg_off); } + set_helper_retaddr(ra); + while (reg_off <= reg_last) { uint64_t pg = vg[reg_off >> 6]; do { @@ -529,6 +531,8 @@ void sme_ld1(CPUARMState *env, void *za, uint64_t *vg, } while (reg_off <= reg_last && (reg_off & 63)); } + clear_helper_retaddr(); + /* * Use the slow path to manage the cross-page misalignment. * But we know this is RAM and cannot trap. @@ -543,6 +547,8 @@ void sme_ld1(CPUARMState *env, void *za, uint64_t *vg, reg_last = info.reg_off_last[1]; host = info.page[1].host; + set_helper_retaddr(ra); + do { uint64_t pg = vg[reg_off >> 6]; do { @@ -554,6 +560,8 @@ void sme_ld1(CPUARMState *env, void *za, uint64_t *vg, reg_off += esize; } while (reg_off & 63); } while (reg_off <= reg_last); + + clear_helper_retaddr(); } } @@ -701,6 +709,8 @@ void sme_st1(CPUARMState *env, void *za, uint64_t *vg, reg_last = info.reg_off_last[0]; host = info.page[0].host; + set_helper_retaddr(ra); + while (reg_off <= reg_last) { uint64_t pg = vg[reg_off >> 6]; do { @@ -711,6 +721,8 @@ void sme_st1(CPUARMState *env, void *za, uint64_t *vg, } while (reg_off <= reg_last && (reg_off & 63)); } + clear_helper_retaddr(); + /* * Use the slow path to manage the cross-page misalignment. * But we know this is RAM and cannot trap. @@ -725,6 +737,8 @@ void sme_st1(CPUARMState *env, void *za, uint64_t *vg, reg_last = info.reg_off_last[1]; host = info.page[1].host; + set_helper_retaddr(ra); + do { uint64_t pg = vg[reg_off >> 6]; do { @@ -734,6 +748,8 @@ void sme_st1(CPUARMState *env, void *za, uint64_t *vg, reg_off += 1 << esz; } while (reg_off & 63); } while (reg_off <= reg_last); + + clear_helper_retaddr(); } } diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c index dd49e67d7a..f1ee0e060f 100644 --- a/target/arm/tcg/sve_helper.c +++ b/target/arm/tcg/sve_helper.c @@ -5738,6 +5738,8 @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr, reg_last = info.reg_off_last[0]; host = info.page[0].host; + set_helper_retaddr(retaddr); + while (reg_off <= reg_last) { uint64_t pg = vg[reg_off >> 6]; do { @@ -5752,6 +5754,8 @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr, } while (reg_off <= reg_last && (reg_off & 63)); } + clear_helper_retaddr(); + /* * Use the slow path to manage the cross-page misalignment. * But we know this is RAM and cannot trap. @@ -5771,6 +5775,8 @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr, reg_last = info.reg_off_last[1]; host = info.page[1].host; + set_helper_retaddr(retaddr); + do { uint64_t pg = vg[reg_off >> 6]; do { @@ -5784,6 +5790,8 @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr, mem_off += N << msz; } while (reg_off & 63); } while (reg_off <= reg_last); + + clear_helper_retaddr(); } } @@ -5934,15 +5942,11 @@ DO_LDN_2(4, dd, MO_64) /* * Load contiguous data, first-fault and no-fault. * - * For user-only, one could argue that we should hold the mmap_lock during - * the operation so that there is no race between page_check_range and the - * load operation. However, unmapping pages out from under a running thread - * is extraordinarily unlikely. This theoretical race condition also affects - * linux-user/ in its get_user/put_user macros. - * - * TODO: Construct some helpers, written in assembly, that interact with - * host_signal_handler to produce memory ops which can properly report errors - * without racing. + * For user-only, we control the race between page_check_range and + * another thread's munmap by using set/clear_helper_retaddr. Any + * SEGV that occurs between those markers is assumed to be because + * the guest page vanished. Keep that block as small as possible + * so that unrelated QEMU bugs are not blamed on the guest. */ /* Fault on byte I. All bits in FFR from I are cleared. The vector @@ -6093,6 +6097,8 @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr, reg_last = info.reg_off_last[0]; host = info.page[0].host; + set_helper_retaddr(retaddr); + do { uint64_t pg = *(uint64_t *)(vg + (reg_off >> 3)); do { @@ -6101,9 +6107,11 @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr, (cpu_watchpoint_address_matches (env_cpu(env), addr + mem_off, 1 << msz) & BP_MEM_READ)) { + clear_helper_retaddr(); goto do_fault; } if (mtedesc && !mte_probe(env, mtedesc, addr + mem_off)) { + clear_helper_retaddr(); goto do_fault; } host_fn(vd, reg_off, host + mem_off); @@ -6113,6 +6121,8 @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr, } while (reg_off <= reg_last && (reg_off & 63)); } while (reg_off <= reg_last); + clear_helper_retaddr(); + /* * MemSingleNF is allowed to fail for any reason. We have special * code above to handle the first element crossing a page boundary. @@ -6348,6 +6358,8 @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, reg_last = info.reg_off_last[0]; host = info.page[0].host; + set_helper_retaddr(retaddr); + while (reg_off <= reg_last) { uint64_t pg = vg[reg_off >> 6]; do { @@ -6362,6 +6374,8 @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, } while (reg_off <= reg_last && (reg_off & 63)); } + clear_helper_retaddr(); + /* * Use the slow path to manage the cross-page misalignment. * But we know this is RAM and cannot trap. @@ -6381,6 +6395,8 @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, reg_last = info.reg_off_last[1]; host = info.page[1].host; + set_helper_retaddr(retaddr); + do { uint64_t pg = vg[reg_off >> 6]; do { @@ -6394,6 +6410,8 @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, mem_off += N << msz; } while (reg_off & 63); } while (reg_off <= reg_last); + + clear_helper_retaddr(); } } @@ -6560,7 +6578,9 @@ void sve_ld1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, if (unlikely(info.flags & TLB_MMIO)) { tlb_fn(env, &scratch, reg_off, addr, retaddr); } else { + set_helper_retaddr(retaddr); host_fn(&scratch, reg_off, info.host); + clear_helper_retaddr(); } } else { /* Element crosses the page boundary. */ @@ -6782,7 +6802,9 @@ void sve_ldff1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, goto fault; } + set_helper_retaddr(retaddr); host_fn(vd, reg_off, info.host); + clear_helper_retaddr(); } reg_off += esize; } while (reg_off & 63); @@ -6986,7 +7008,9 @@ void sve_st1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, do { void *h = host[i]; if (likely(h != NULL)) { + set_helper_retaddr(retaddr); host_fn(vd, reg_off, h); + clear_helper_retaddr(); } else if ((vg[reg_off >> 6] >> (reg_off & 63)) & 1) { target_ulong addr = base + (off_fn(vm, reg_off) << scale); tlb_fn(env, vd, reg_off, addr, retaddr); diff --git a/target/m68k/Kconfig b/target/m68k/Kconfig index 9eae71486f..23aae24ebe 100644 --- a/target/m68k/Kconfig +++ b/target/m68k/Kconfig @@ -1,3 +1,3 @@ config M68K bool - select SEMIHOSTING + imply SEMIHOSTING if TCG diff --git a/target/m68k/meson.build b/target/m68k/meson.build index 8d3f9ce288..4d213daaf6 100644 --- a/target/m68k/meson.build +++ b/target/m68k/meson.build @@ -11,9 +11,12 @@ m68k_ss.add(files( m68k_system_ss = ss.source_set() m68k_system_ss.add(files( - 'm68k-semi.c', 'monitor.c' )) +m68k_system_ss.add(when: ['CONFIG_SEMIHOSTING'], + if_true: files('m68k-semi.c'), + if_false: files('semihosting-stub.c') +) target_arch += {'m68k': m68k_ss} target_system_arch += {'m68k': m68k_system_ss} diff --git a/target/m68k/semihosting-stub.c b/target/m68k/semihosting-stub.c new file mode 100644 index 0000000000..d6a5965e29 --- /dev/null +++ b/target/m68k/semihosting-stub.c @@ -0,0 +1,15 @@ +/* + * m68k/ColdFire semihosting stub + * + * SPDX-FileContributor: Philippe Mathieu-Daudé <philmd@linaro.org> + * SPDX-FileCopyrightText: 2024 Linaro Ltd. + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "cpu.h" + +void do_m68k_semihosting(CPUM68KState *env, int nr) +{ + g_assert_not_reached(); +} diff --git a/target/mips/Kconfig b/target/mips/Kconfig index eb19c94c7d..876048b150 100644 --- a/target/mips/Kconfig +++ b/target/mips/Kconfig @@ -1,6 +1,6 @@ config MIPS bool - select SEMIHOSTING + imply SEMIHOSTING if TCG config MIPS64 bool diff --git a/target/mips/tcg/sysemu/meson.build b/target/mips/tcg/sysemu/meson.build index ec665a4b1e..911341ac37 100644 --- a/target/mips/tcg/sysemu/meson.build +++ b/target/mips/tcg/sysemu/meson.build @@ -1,10 +1,12 @@ mips_system_ss.add(files( 'cp0_helper.c', - 'mips-semi.c', 'special_helper.c', 'tlb_helper.c', )) - +mips_system_ss.add(when: ['CONFIG_SEMIHOSTING'], + if_true: files('mips-semi.c'), + if_false: files('semihosting-stub.c') +) mips_system_ss.add(when: 'TARGET_MIPS64', if_true: files( 'lcsr_helper.c', )) diff --git a/target/mips/tcg/sysemu/semihosting-stub.c b/target/mips/tcg/sysemu/semihosting-stub.c new file mode 100644 index 0000000000..7ae27d746f --- /dev/null +++ b/target/mips/tcg/sysemu/semihosting-stub.c @@ -0,0 +1,15 @@ +/* + * MIPS semihosting stub + * + * SPDX-FileContributor: Philippe Mathieu-Daudé <philmd@linaro.org> + * SPDX-FileCopyrightText: 2024 Linaro Ltd. + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "internal.h" + +void mips_semihosting(CPUMIPSState *env) +{ + g_assert_not_reached(); +} diff --git a/target/ppc/helper.h b/target/ppc/helper.h index 76b8f25c77..4fa089cbf9 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -46,8 +46,10 @@ DEF_HELPER_FLAGS_3(stmw, TCG_CALL_NO_WG, void, env, tl, i32) DEF_HELPER_4(lsw, void, env, tl, i32, i32) DEF_HELPER_5(lswx, void, env, tl, i32, i32, i32) DEF_HELPER_FLAGS_4(stsw, TCG_CALL_NO_WG, void, env, tl, i32, i32) -DEF_HELPER_FLAGS_3(dcbz, TCG_CALL_NO_WG, void, env, tl, i32) -DEF_HELPER_FLAGS_3(dcbzep, TCG_CALL_NO_WG, void, env, tl, i32) +DEF_HELPER_FLAGS_3(dcbz, TCG_CALL_NO_WG, void, env, tl, int) +#ifdef TARGET_PPC64 +DEF_HELPER_FLAGS_2(dcbzl, TCG_CALL_NO_WG, void, env, tl) +#endif DEF_HELPER_FLAGS_2(icbi, TCG_CALL_NO_WG, void, env, tl) DEF_HELPER_FLAGS_2(icbiep, TCG_CALL_NO_WG, void, env, tl) DEF_HELPER_5(lscbx, tl, env, tl, i32, i32, i32) diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c index f88155ad45..953dd08d5d 100644 --- a/target/ppc/mem_helper.c +++ b/target/ppc/mem_helper.c @@ -271,51 +271,59 @@ void helper_stsw(CPUPPCState *env, target_ulong addr, uint32_t nb, } static void dcbz_common(CPUPPCState *env, target_ulong addr, - uint32_t opcode, bool epid, uintptr_t retaddr) + int mmu_idx, int dcbz_size, uintptr_t retaddr) { - target_ulong mask, dcbz_size = env->dcache_line_size; - uint32_t i; + target_ulong mask = ~(target_ulong)(dcbz_size - 1); void *haddr; - int mmu_idx = epid ? PPC_TLB_EPID_STORE : ppc_env_mmu_index(env, false); - -#if defined(TARGET_PPC64) - /* Check for dcbz vs dcbzl on 970 */ - if (env->excp_model == POWERPC_EXCP_970 && - !(opcode & 0x00200000) && ((env->spr[SPR_970_HID5] >> 7) & 0x3) == 1) { - dcbz_size = 32; - } -#endif /* Align address */ - mask = ~(dcbz_size - 1); addr &= mask; /* Check reservation */ - if ((env->reserve_addr & mask) == addr) { + if (unlikely((env->reserve_addr & mask) == addr)) { env->reserve_addr = (target_ulong)-1ULL; } /* Try fast path translate */ +#ifdef CONFIG_USER_ONLY + haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, mmu_idx); +#else haddr = probe_write(env, addr, dcbz_size, mmu_idx, retaddr); - if (haddr) { - memset(haddr, 0, dcbz_size); - } else { + if (unlikely(!haddr)) { /* Slow path */ - for (i = 0; i < dcbz_size; i += 8) { + for (int i = 0; i < dcbz_size; i += 8) { cpu_stq_mmuidx_ra(env, addr + i, 0, mmu_idx, retaddr); } + return; } +#endif + + set_helper_retaddr(retaddr); + memset(haddr, 0, dcbz_size); + clear_helper_retaddr(); } -void helper_dcbz(CPUPPCState *env, target_ulong addr, uint32_t opcode) +void helper_dcbz(CPUPPCState *env, target_ulong addr, int mmu_idx) { - dcbz_common(env, addr, opcode, false, GETPC()); + dcbz_common(env, addr, mmu_idx, env->dcache_line_size, GETPC()); } -void helper_dcbzep(CPUPPCState *env, target_ulong addr, uint32_t opcode) +#ifdef TARGET_PPC64 +void helper_dcbzl(CPUPPCState *env, target_ulong addr) { - dcbz_common(env, addr, opcode, true, GETPC()); + int dcbz_size = env->dcache_line_size; + + /* + * The translator checked for POWERPC_EXCP_970. + * All that's left is to check HID5. + */ + if (((env->spr[SPR_970_HID5] >> 7) & 0x3) == 1) { + dcbz_size = 32; + } + + dcbz_common(env, addr, ppc_env_mmu_index(env, false), dcbz_size, GETPC()); } +#endif void helper_icbi(CPUPPCState *env, target_ulong addr) { diff --git a/target/ppc/translate.c b/target/ppc/translate.c index 0bc16d7251..cba943a49d 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -178,6 +178,7 @@ struct DisasContext { /* Translation flags */ MemOp default_tcg_memop_mask; #if defined(TARGET_PPC64) + powerpc_excp_t excp_model; bool sf_mode; bool has_cfar; bool has_bhrb; @@ -4445,27 +4446,29 @@ static void gen_dcblc(DisasContext *ctx) /* dcbz */ static void gen_dcbz(DisasContext *ctx) { - TCGv tcgv_addr; - TCGv_i32 tcgv_op; + TCGv tcgv_addr = tcg_temp_new(); gen_set_access_type(ctx, ACCESS_CACHE); - tcgv_addr = tcg_temp_new(); - tcgv_op = tcg_constant_i32(ctx->opcode & 0x03FF000); gen_addr_reg_index(ctx, tcgv_addr); - gen_helper_dcbz(tcg_env, tcgv_addr, tcgv_op); + +#ifdef TARGET_PPC64 + if (ctx->excp_model == POWERPC_EXCP_970 && !(ctx->opcode & 0x00200000)) { + gen_helper_dcbzl(tcg_env, tcgv_addr); + return; + } +#endif + + gen_helper_dcbz(tcg_env, tcgv_addr, tcg_constant_i32(ctx->mem_idx)); } /* dcbzep */ static void gen_dcbzep(DisasContext *ctx) { - TCGv tcgv_addr; - TCGv_i32 tcgv_op; + TCGv tcgv_addr = tcg_temp_new(); gen_set_access_type(ctx, ACCESS_CACHE); - tcgv_addr = tcg_temp_new(); - tcgv_op = tcg_constant_i32(ctx->opcode & 0x03FF000); gen_addr_reg_index(ctx, tcgv_addr); - gen_helper_dcbzep(tcg_env, tcgv_addr, tcgv_op); + gen_helper_dcbz(tcg_env, tcgv_addr, tcg_constant_i32(PPC_TLB_EPID_STORE)); } /* dst / dstt */ @@ -6486,6 +6489,7 @@ static void ppc_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) ctx->default_tcg_memop_mask = ctx->le_mode ? MO_LE : MO_BE; ctx->flags = env->flags; #if defined(TARGET_PPC64) + ctx->excp_model = env->excp_model; ctx->sf_mode = (hflags >> HFLAGS_64) & 1; ctx->has_cfar = !!(env->flags & POWERPC_FLAG_CFAR); ctx->has_bhrb = !!(env->flags & POWERPC_FLAG_BHRB); diff --git a/target/riscv/Kconfig b/target/riscv/Kconfig index 5f30df22f2..c332616d36 100644 --- a/target/riscv/Kconfig +++ b/target/riscv/Kconfig @@ -1,9 +1,9 @@ config RISCV32 bool - select ARM_COMPATIBLE_SEMIHOSTING # for do_common_semihosting() + imply ARM_COMPATIBLE_SEMIHOSTING if TCG select DEVICE_TREE # needed by boot.c config RISCV64 bool - select ARM_COMPATIBLE_SEMIHOSTING # for do_common_semihosting() + imply ARM_COMPATIBLE_SEMIHOSTING if TCG select DEVICE_TREE # needed by boot.c diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 1b4d5a8e37..10a52ceb5b 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -474,7 +474,6 @@ vext_ldff(void *vd, void *v0, target_ulong base, vext_ldst_elem_fn *ldst_elem, uint32_t log2_esz, uintptr_t ra) { - void *host; uint32_t i, k, vl = 0; uint32_t nf = vext_nf(desc); uint32_t vm = vext_vm(desc); @@ -493,27 +492,31 @@ vext_ldff(void *vd, void *v0, target_ulong base, } addr = adjust_addr(env, base + i * (nf << log2_esz)); if (i == 0) { + /* Allow fault on first element. */ probe_pages(env, addr, nf << log2_esz, ra, MMU_DATA_LOAD); } else { - /* if it triggers an exception, no need to check watchpoint */ remain = nf << log2_esz; while (remain > 0) { + void *host; + int flags; + offset = -(addr | TARGET_PAGE_MASK); - host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_index); - if (host) { -#ifdef CONFIG_USER_ONLY - if (!page_check_range(addr, offset, PAGE_READ)) { - vl = i; - goto ProbeSuccess; - } -#else - probe_pages(env, addr, offset, ra, MMU_DATA_LOAD); -#endif - } else { + + /* Probe nonfault on subsequent elements. */ + flags = probe_access_flags(env, addr, offset, MMU_DATA_LOAD, + mmu_index, true, &host, 0); + + /* + * Stop if invalid (unmapped) or mmio (transaction may fail). + * Do not stop if watchpoint, as the spec says that + * first-fault should continue to access the same + * elements regardless of any watchpoint. + */ + if (flags & ~TLB_WATCHPOINT) { vl = i; goto ProbeSuccess; } - if (remain <= offset) { + if (remain <= offset) { break; } remain -= offset; diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c index 977fbc6522..94dd798b4c 100644 --- a/target/s390x/cpu_models_sysemu.c +++ b/target/s390x/cpu_models_sysemu.c @@ -174,11 +174,15 @@ static void cpu_info_from_model(CpuModelInfo *info, const S390CPUModel *model, bool delta_changes) { QDict *qdict = qdict_new(); - S390FeatBitmap bitmap; + S390FeatBitmap bitmap, deprecated; /* always fallback to the static base model */ info->name = g_strdup_printf("%s-base", model->def->name); + /* features flagged as deprecated */ + bitmap_zero(deprecated, S390_FEAT_MAX); + s390_get_deprecated_features(deprecated); + if (delta_changes) { /* features deleted from the base feature set */ bitmap_andnot(bitmap, model->def->base_feat, model->features, @@ -193,6 +197,9 @@ static void cpu_info_from_model(CpuModelInfo *info, const S390CPUModel *model, if (!bitmap_empty(bitmap, S390_FEAT_MAX)) { s390_feat_bitmap_to_ascii(bitmap, qdict, qdict_add_enabled_feat); } + + /* deprecated features that are a subset of the model's enabled features */ + bitmap_and(deprecated, deprecated, model->features, S390_FEAT_MAX); } else { /* expand all features */ s390_feat_bitmap_to_ascii(model->features, qdict, @@ -207,12 +214,7 @@ static void cpu_info_from_model(CpuModelInfo *info, const S390CPUModel *model, info->props = QOBJECT(qdict); } - /* features flagged as deprecated */ - bitmap_zero(bitmap, S390_FEAT_MAX); - s390_get_deprecated_features(bitmap); - - bitmap_and(bitmap, bitmap, model->def->full_feat, S390_FEAT_MAX); - s390_feat_bitmap_to_ascii(bitmap, &info->deprecated_props, list_add_feat); + s390_feat_bitmap_to_ascii(deprecated, &info->deprecated_props, list_add_feat); info->has_deprecated_props = !!info->deprecated_props; } diff --git a/target/s390x/tcg/mem_helper.c b/target/s390x/tcg/mem_helper.c index 6cdbc34178..0e12dae2aa 100644 --- a/target/s390x/tcg/mem_helper.c +++ b/target/s390x/tcg/mem_helper.c @@ -225,10 +225,7 @@ static void do_access_memset(CPUS390XState *env, vaddr vaddr, char *haddr, uint8_t byte, uint16_t size, int mmu_idx, uintptr_t ra) { -#ifdef CONFIG_USER_ONLY - memset(haddr, byte, size); -#else - if (likely(haddr)) { + if (user_or_likely(haddr)) { memset(haddr, byte, size); } else { MemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); @@ -236,20 +233,19 @@ static void do_access_memset(CPUS390XState *env, vaddr vaddr, char *haddr, cpu_stb_mmu(env, vaddr + i, byte, oi, ra); } } -#endif } static void access_memset(CPUS390XState *env, S390Access *desta, uint8_t byte, uintptr_t ra) { - + set_helper_retaddr(ra); do_access_memset(env, desta->vaddr1, desta->haddr1, byte, desta->size1, desta->mmu_idx, ra); - if (likely(!desta->size2)) { - return; + if (unlikely(desta->size2)) { + do_access_memset(env, desta->vaddr2, desta->haddr2, byte, + desta->size2, desta->mmu_idx, ra); } - do_access_memset(env, desta->vaddr2, desta->haddr2, byte, desta->size2, - desta->mmu_idx, ra); + clear_helper_retaddr(); } static uint8_t access_get_byte(CPUS390XState *env, S390Access *access, @@ -300,41 +296,39 @@ static void access_memmove(CPUS390XState *env, S390Access *desta, S390Access *srca, uintptr_t ra) { int len = desta->size1 + desta->size2; - int diff; assert(len == srca->size1 + srca->size2); /* Fallback to slow access in case we don't have access to all host pages */ - if (unlikely(!desta->haddr1 || (desta->size2 && !desta->haddr2) || - !srca->haddr1 || (srca->size2 && !srca->haddr2))) { - int i; - - for (i = 0; i < len; i++) { - uint8_t byte = access_get_byte(env, srca, i, ra); - - access_set_byte(env, desta, i, byte, ra); - } - return; - } - - diff = desta->size1 - srca->size1; - if (likely(diff == 0)) { - memmove(desta->haddr1, srca->haddr1, srca->size1); - if (unlikely(srca->size2)) { - memmove(desta->haddr2, srca->haddr2, srca->size2); - } - } else if (diff > 0) { - memmove(desta->haddr1, srca->haddr1, srca->size1); - memmove(desta->haddr1 + srca->size1, srca->haddr2, diff); - if (likely(desta->size2)) { - memmove(desta->haddr2, srca->haddr2 + diff, desta->size2); + if (user_or_likely(desta->haddr1 && + srca->haddr1 && + (!desta->size2 || desta->haddr2) && + (!srca->size2 || srca->haddr2))) { + int diff = desta->size1 - srca->size1; + + if (likely(diff == 0)) { + memmove(desta->haddr1, srca->haddr1, srca->size1); + if (unlikely(srca->size2)) { + memmove(desta->haddr2, srca->haddr2, srca->size2); + } + } else if (diff > 0) { + memmove(desta->haddr1, srca->haddr1, srca->size1); + memmove(desta->haddr1 + srca->size1, srca->haddr2, diff); + if (likely(desta->size2)) { + memmove(desta->haddr2, srca->haddr2 + diff, desta->size2); + } + } else { + diff = -diff; + memmove(desta->haddr1, srca->haddr1, desta->size1); + memmove(desta->haddr2, srca->haddr1 + desta->size1, diff); + if (likely(srca->size2)) { + memmove(desta->haddr2 + diff, srca->haddr2, srca->size2); + } } } else { - diff = -diff; - memmove(desta->haddr1, srca->haddr1, desta->size1); - memmove(desta->haddr2, srca->haddr1 + desta->size1, diff); - if (likely(srca->size2)) { - memmove(desta->haddr2 + diff, srca->haddr2, srca->size2); + for (int i = 0; i < len; i++) { + uint8_t byte = access_get_byte(env, srca, i, ra); + access_set_byte(env, desta, i, byte, ra); } } } @@ -372,6 +366,8 @@ static uint32_t do_helper_nc(CPUS390XState *env, uint32_t l, uint64_t dest, access_prepare(&srca1, env, src, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&srca2, env, dest, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&desta, env, dest, l, MMU_DATA_STORE, mmu_idx, ra); + set_helper_retaddr(ra); + for (i = 0; i < l; i++) { const uint8_t x = access_get_byte(env, &srca1, i, ra) & access_get_byte(env, &srca2, i, ra); @@ -379,6 +375,8 @@ static uint32_t do_helper_nc(CPUS390XState *env, uint32_t l, uint64_t dest, c |= x; access_set_byte(env, &desta, i, x, ra); } + + clear_helper_retaddr(); return c != 0; } @@ -413,6 +411,7 @@ static uint32_t do_helper_xc(CPUS390XState *env, uint32_t l, uint64_t dest, return 0; } + set_helper_retaddr(ra); for (i = 0; i < l; i++) { const uint8_t x = access_get_byte(env, &srca1, i, ra) ^ access_get_byte(env, &srca2, i, ra); @@ -420,6 +419,7 @@ static uint32_t do_helper_xc(CPUS390XState *env, uint32_t l, uint64_t dest, c |= x; access_set_byte(env, &desta, i, x, ra); } + clear_helper_retaddr(); return c != 0; } @@ -447,6 +447,8 @@ static uint32_t do_helper_oc(CPUS390XState *env, uint32_t l, uint64_t dest, access_prepare(&srca1, env, src, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&srca2, env, dest, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&desta, env, dest, l, MMU_DATA_STORE, mmu_idx, ra); + set_helper_retaddr(ra); + for (i = 0; i < l; i++) { const uint8_t x = access_get_byte(env, &srca1, i, ra) | access_get_byte(env, &srca2, i, ra); @@ -454,6 +456,8 @@ static uint32_t do_helper_oc(CPUS390XState *env, uint32_t l, uint64_t dest, c |= x; access_set_byte(env, &desta, i, x, ra); } + + clear_helper_retaddr(); return c != 0; } @@ -490,11 +494,13 @@ static uint32_t do_helper_mvc(CPUS390XState *env, uint32_t l, uint64_t dest, } else if (!is_destructive_overlap(env, dest, src, l)) { access_memmove(env, &desta, &srca, ra); } else { + set_helper_retaddr(ra); for (i = 0; i < l; i++) { uint8_t byte = access_get_byte(env, &srca, i, ra); access_set_byte(env, &desta, i, byte, ra); } + clear_helper_retaddr(); } return env->cc_op; @@ -520,10 +526,12 @@ void HELPER(mvcrl)(CPUS390XState *env, uint64_t l, uint64_t dest, uint64_t src) access_prepare(&srca, env, src, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&desta, env, dest, l, MMU_DATA_STORE, mmu_idx, ra); + set_helper_retaddr(ra); for (i = l - 1; i >= 0; i--) { uint8_t byte = access_get_byte(env, &srca, i, ra); access_set_byte(env, &desta, i, byte, ra); } + clear_helper_retaddr(); } /* move inverse */ @@ -540,11 +548,13 @@ void HELPER(mvcin)(CPUS390XState *env, uint32_t l, uint64_t dest, uint64_t src) src = wrap_address(env, src - l + 1); access_prepare(&srca, env, src, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&desta, env, dest, l, MMU_DATA_STORE, mmu_idx, ra); + + set_helper_retaddr(ra); for (i = 0; i < l; i++) { const uint8_t x = access_get_byte(env, &srca, l - i - 1, ra); - access_set_byte(env, &desta, i, x, ra); } + clear_helper_retaddr(); } /* move numerics */ @@ -561,12 +571,15 @@ void HELPER(mvn)(CPUS390XState *env, uint32_t l, uint64_t dest, uint64_t src) access_prepare(&srca1, env, src, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&srca2, env, dest, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&desta, env, dest, l, MMU_DATA_STORE, mmu_idx, ra); + + set_helper_retaddr(ra); for (i = 0; i < l; i++) { const uint8_t x = (access_get_byte(env, &srca1, i, ra) & 0x0f) | (access_get_byte(env, &srca2, i, ra) & 0xf0); access_set_byte(env, &desta, i, x, ra); } + clear_helper_retaddr(); } /* move with offset */ @@ -586,6 +599,8 @@ void HELPER(mvo)(CPUS390XState *env, uint32_t l, uint64_t dest, uint64_t src) /* Handle rightmost byte */ byte_dest = cpu_ldub_data_ra(env, dest + len_dest - 1, ra); + + set_helper_retaddr(ra); byte_src = access_get_byte(env, &srca, len_src - 1, ra); byte_dest = (byte_dest & 0x0f) | (byte_src << 4); access_set_byte(env, &desta, len_dest - 1, byte_dest, ra); @@ -601,6 +616,7 @@ void HELPER(mvo)(CPUS390XState *env, uint32_t l, uint64_t dest, uint64_t src) byte_dest |= byte_src << 4; access_set_byte(env, &desta, i, byte_dest, ra); } + clear_helper_retaddr(); } /* move zones */ @@ -617,12 +633,15 @@ void HELPER(mvz)(CPUS390XState *env, uint32_t l, uint64_t dest, uint64_t src) access_prepare(&srca1, env, src, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&srca2, env, dest, l, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&desta, env, dest, l, MMU_DATA_STORE, mmu_idx, ra); + + set_helper_retaddr(ra); for (i = 0; i < l; i++) { const uint8_t x = (access_get_byte(env, &srca1, i, ra) & 0xf0) | (access_get_byte(env, &srca2, i, ra) & 0x0f); access_set_byte(env, &desta, i, x, ra); } + clear_helper_retaddr(); } /* compare unsigned byte arrays */ @@ -967,15 +986,19 @@ uint32_t HELPER(mvst)(CPUS390XState *env, uint32_t r1, uint32_t r2) */ access_prepare(&srca, env, s, len, MMU_DATA_LOAD, mmu_idx, ra); access_prepare(&desta, env, d, len, MMU_DATA_STORE, mmu_idx, ra); + + set_helper_retaddr(ra); for (i = 0; i < len; i++) { const uint8_t v = access_get_byte(env, &srca, i, ra); access_set_byte(env, &desta, i, v, ra); if (v == c) { + clear_helper_retaddr(); set_address_zero(env, r1, d + i); return 1; } } + clear_helper_retaddr(); set_address_zero(env, r1, d + len); set_address_zero(env, r2, s + len); return 3; @@ -1066,6 +1089,7 @@ static inline uint32_t do_mvcl(CPUS390XState *env, *dest = wrap_address(env, *dest + len); } else { access_prepare(&desta, env, *dest, len, MMU_DATA_STORE, mmu_idx, ra); + set_helper_retaddr(ra); /* The remaining length selects the padding byte. */ for (i = 0; i < len; (*destlen)--, i++) { @@ -1075,6 +1099,7 @@ static inline uint32_t do_mvcl(CPUS390XState *env, access_set_byte(env, &desta, i, pad >> 8, ra); } } + clear_helper_retaddr(); *dest = wrap_address(env, *dest + len); } diff --git a/target/xtensa/Kconfig b/target/xtensa/Kconfig index 5e46049262..e8c2598c4d 100644 --- a/target/xtensa/Kconfig +++ b/target/xtensa/Kconfig @@ -1,3 +1,3 @@ config XTENSA bool - select SEMIHOSTING + imply SEMIHOSTING if TCG diff --git a/tests/Makefile.include b/tests/Makefile.include index d39d5dd6a4..6618bfed70 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -97,7 +97,7 @@ endif # Controls the output generated by Avocado when running tests. # Any number of command separated loggers are accepted. For more # information please refer to "avocado --help". -AVOCADO_SHOW=app +AVOCADO_SHOW?=app ifndef AVOCADO_TAGS AVOCADO_CMDLINE_TAGS=$(patsubst %-softmmu,-t arch:%, \ $(filter %-softmmu,$(TARGETS))) diff --git a/tests/avocado/avocado_qemu/__init__.py b/tests/avocado/avocado_qemu/__init__.py index 304c428168..a3da2a96bb 100644 --- a/tests/avocado/avocado_qemu/__init__.py +++ b/tests/avocado/avocado_qemu/__init__.py @@ -10,7 +10,6 @@ import logging import os -import shutil import subprocess import sys import tempfile @@ -18,7 +17,7 @@ import time import uuid import avocado -from avocado.utils import cloudinit, datadrainer, process, ssh, vmimage +from avocado.utils import ssh from avocado.utils.path import find_command from qemu.machine import QEMUMachine @@ -32,14 +31,6 @@ from qemu.utils import (get_info_usernet_hostfwd_port, kvm_available, #: and build tree, it will not be accurate. BUILD_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.dirname(__file__)))) -if os.path.islink(os.path.dirname(os.path.dirname(__file__))): - # The link to the avocado tests dir in the source code directory - lnk = os.path.dirname(os.path.dirname(__file__)) - #: The QEMU root source directory - SOURCE_DIR = os.path.dirname(os.path.dirname(os.readlink(lnk))) -else: - SOURCE_DIR = BUILD_DIR - def has_cmd(name, args=None): """ @@ -451,231 +442,3 @@ class LinuxSSHMixIn: break else: self.fail('"%s" output does not contain "%s"' % (cmd, exp)) - -class LinuxDistro: - """Represents a Linux distribution - - Holds information of known distros. - """ - #: A collection of known distros and their respective image checksum - KNOWN_DISTROS = { - 'fedora': { - '31': { - 'x86_64': - {'checksum': ('e3c1b309d9203604922d6e255c2c5d09' - '8a309c2d46215d8fc026954f3c5c27a0'), - 'pxeboot_url': ('https://archives.fedoraproject.org/' - 'pub/archive/fedora/linux/releases/31/' - 'Everything/x86_64/os/images/pxeboot/'), - 'kernel_params': ('root=UUID=b1438b9b-2cab-4065-a99a-' - '08a96687f73c ro no_timer_check ' - 'net.ifnames=0 console=tty1 ' - 'console=ttyS0,115200n8'), - }, - 'aarch64': - {'checksum': ('1e18d9c0cf734940c4b5d5ec592facae' - 'd2af0ad0329383d5639c997fdf16fe49'), - 'pxeboot_url': 'https://archives.fedoraproject.org/' - 'pub/archive/fedora/linux/releases/31/' - 'Everything/aarch64/os/images/pxeboot/', - 'kernel_params': ('root=UUID=b6950a44-9f3c-4076-a9c2-' - '355e8475b0a7 ro earlyprintk=pl011,0x9000000' - ' ignore_loglevel no_timer_check' - ' printk.time=1 rd_NO_PLYMOUTH' - ' console=ttyAMA0'), - }, - 'ppc64': - {'checksum': ('7c3528b85a3df4b2306e892199a9e1e4' - '3f991c506f2cc390dc4efa2026ad2f58')}, - 's390x': - {'checksum': ('4caaab5a434fd4d1079149a072fdc789' - '1e354f834d355069ca982fdcaf5a122d')}, - }, - '32': { - 'aarch64': - {'checksum': ('b367755c664a2d7a26955bbfff985855' - 'adfa2ca15e908baf15b4b176d68d3967'), - 'pxeboot_url': ('http://dl.fedoraproject.org/pub/fedora/linux/' - 'releases/32/Server/aarch64/os/images/' - 'pxeboot/'), - 'kernel_params': ('root=UUID=3df75b65-be8d-4db4-8655-' - '14d95c0e90c5 ro no_timer_check net.ifnames=0' - ' console=tty1 console=ttyS0,115200n8'), - }, - }, - '33': { - 'aarch64': - {'checksum': ('e7f75cdfd523fe5ac2ca9eeece68edc1' - 'a81f386a17f969c1d1c7c87031008a6b'), - 'pxeboot_url': ('http://dl.fedoraproject.org/pub/fedora/linux/' - 'releases/33/Server/aarch64/os/images/' - 'pxeboot/'), - 'kernel_params': ('root=UUID=d20b3ffa-6397-4a63-a734-' - '1126a0208f8a ro no_timer_check net.ifnames=0' - ' console=tty1 console=ttyS0,115200n8' - ' console=tty0'), - }, - }, - } - } - - def __init__(self, name, version, arch): - self.name = name - self.version = version - self.arch = arch - try: - info = self.KNOWN_DISTROS.get(name).get(version).get(arch) - except AttributeError: - # Unknown distro - info = None - self._info = info or {} - - @property - def checksum(self): - """Gets the cloud-image file checksum""" - return self._info.get('checksum', None) - - @checksum.setter - def checksum(self, value): - self._info['checksum'] = value - - @property - def pxeboot_url(self): - """Gets the repository url where pxeboot files can be found""" - return self._info.get('pxeboot_url', None) - - @property - def default_kernel_params(self): - """Gets the default kernel parameters""" - return self._info.get('kernel_params', None) - - -class LinuxTest(LinuxSSHMixIn, QemuSystemTest): - """Facilitates having a cloud-image Linux based available. - - For tests that intend to interact with guests, this is a better choice - to start with than the more vanilla `QemuSystemTest` class. - """ - - distro = None - username = 'root' - password = 'password' - smp = '2' - memory = '1024' - - def _set_distro(self): - distro_name = self.params.get( - 'distro', - default=self._get_unique_tag_val('distro')) - if not distro_name: - distro_name = 'fedora' - - distro_version = self.params.get( - 'distro_version', - default=self._get_unique_tag_val('distro_version')) - if not distro_version: - distro_version = '31' - - self.distro = LinuxDistro(distro_name, distro_version, self.arch) - - # The distro checksum behaves differently than distro name and - # version. First, it does not respect a tag with the same - # name, given that it's not expected to be used for filtering - # (distro name versions are the natural choice). Second, the - # order of precedence is: parameter, attribute and then value - # from KNOWN_DISTROS. - distro_checksum = self.params.get('distro_checksum', - default=None) - if distro_checksum: - self.distro.checksum = distro_checksum - - def setUp(self, ssh_pubkey=None, network_device_type='virtio-net'): - super().setUp() - self.require_netdev('user') - self._set_distro() - self.vm.add_args('-smp', self.smp) - self.vm.add_args('-m', self.memory) - # The following network device allows for SSH connections - self.vm.add_args('-netdev', 'user,id=vnet,hostfwd=:127.0.0.1:0-:22', - '-device', '%s,netdev=vnet' % network_device_type) - self.set_up_boot() - if ssh_pubkey is None: - ssh_pubkey, self.ssh_key = self.set_up_existing_ssh_keys() - self.set_up_cloudinit(ssh_pubkey) - - def set_up_existing_ssh_keys(self): - ssh_public_key = os.path.join(SOURCE_DIR, 'tests', 'keys', 'id_rsa.pub') - source_private_key = os.path.join(SOURCE_DIR, 'tests', 'keys', 'id_rsa') - ssh_dir = os.path.join(self.workdir, '.ssh') - os.mkdir(ssh_dir, mode=0o700) - ssh_private_key = os.path.join(ssh_dir, - os.path.basename(source_private_key)) - shutil.copyfile(source_private_key, ssh_private_key) - os.chmod(ssh_private_key, 0o600) - return (ssh_public_key, ssh_private_key) - - def download_boot(self): - # Set the qemu-img binary. - # If none is available, the test will cancel. - vmimage.QEMU_IMG = super().get_qemu_img() - - self.log.info('Downloading/preparing boot image') - # Fedora 31 only provides ppc64le images - image_arch = self.arch - if self.distro.name == 'fedora': - if image_arch == 'ppc64': - image_arch = 'ppc64le' - - try: - boot = vmimage.get( - self.distro.name, arch=image_arch, version=self.distro.version, - checksum=self.distro.checksum, - algorithm='sha256', - cache_dir=self.cache_dirs[0], - snapshot_dir=self.workdir) - except: - self.cancel('Failed to download/prepare boot image') - return boot.path - - def prepare_cloudinit(self, ssh_pubkey=None): - self.log.info('Preparing cloudinit image') - try: - cloudinit_iso = os.path.join(self.workdir, 'cloudinit.iso') - pubkey_content = None - if ssh_pubkey: - with open(ssh_pubkey) as pubkey: - pubkey_content = pubkey.read() - cloudinit.iso(cloudinit_iso, self.name, - username=self.username, - password=self.password, - # QEMU's hard coded usermode router address - phone_home_host='10.0.2.2', - phone_home_port=self.phone_server.server_port, - authorized_key=pubkey_content) - except Exception: - self.cancel('Failed to prepare the cloudinit image') - return cloudinit_iso - - def set_up_boot(self): - path = self.download_boot() - self.vm.add_args('-drive', 'file=%s' % path) - - def set_up_cloudinit(self, ssh_pubkey=None): - self.phone_server = cloudinit.PhoneHomeServer(('0.0.0.0', 0), - self.name) - cloudinit_iso = self.prepare_cloudinit(ssh_pubkey) - self.vm.add_args('-drive', 'file=%s,format=raw' % cloudinit_iso) - - def launch_and_wait(self, set_up_ssh_connection=True): - self.vm.set_console() - self.vm.launch() - console_drainer = datadrainer.LineLogger(self.vm.console_socket.fileno(), - logger=self.log.getChild('console')) - console_drainer.start() - self.log.info('VM launched, waiting for boot confirmation from guest') - while not self.phone_server.instance_phoned_back: - self.phone_server.handle_request() - - if set_up_ssh_connection: - self.log.info('Setting up the SSH connection') - self.ssh_connect(self.username, self.ssh_key) diff --git a/tests/avocado/avocado_qemu/linuxtest.py b/tests/avocado/avocado_qemu/linuxtest.py new file mode 100644 index 0000000000..e1dc838b1c --- /dev/null +++ b/tests/avocado/avocado_qemu/linuxtest.py @@ -0,0 +1,253 @@ +# Test class and utilities for functional Linux-based tests +# +# Copyright (c) 2018 Red Hat, Inc. +# +# Author: +# Cleber Rosa <crosa@redhat.com> +# +# This work is licensed under the terms of the GNU GPL, version 2 or +# later. See the COPYING file in the top-level directory. + +import os +import shutil + +from avocado.utils import cloudinit, datadrainer, process, vmimage + +from . import LinuxSSHMixIn +from . import QemuSystemTest + +if os.path.islink(os.path.dirname(os.path.dirname(__file__))): + # The link to the avocado tests dir in the source code directory + lnk = os.path.dirname(os.path.dirname(__file__)) + #: The QEMU root source directory + SOURCE_DIR = os.path.dirname(os.path.dirname(os.readlink(lnk))) +else: + SOURCE_DIR = BUILD_DIR + +class LinuxDistro: + """Represents a Linux distribution + + Holds information of known distros. + """ + #: A collection of known distros and their respective image checksum + KNOWN_DISTROS = { + 'fedora': { + '31': { + 'x86_64': + {'checksum': ('e3c1b309d9203604922d6e255c2c5d09' + '8a309c2d46215d8fc026954f3c5c27a0'), + 'pxeboot_url': ('https://archives.fedoraproject.org/' + 'pub/archive/fedora/linux/releases/31/' + 'Everything/x86_64/os/images/pxeboot/'), + 'kernel_params': ('root=UUID=b1438b9b-2cab-4065-a99a-' + '08a96687f73c ro no_timer_check ' + 'net.ifnames=0 console=tty1 ' + 'console=ttyS0,115200n8'), + }, + 'aarch64': + {'checksum': ('1e18d9c0cf734940c4b5d5ec592facae' + 'd2af0ad0329383d5639c997fdf16fe49'), + 'pxeboot_url': 'https://archives.fedoraproject.org/' + 'pub/archive/fedora/linux/releases/31/' + 'Everything/aarch64/os/images/pxeboot/', + 'kernel_params': ('root=UUID=b6950a44-9f3c-4076-a9c2-' + '355e8475b0a7 ro earlyprintk=pl011,0x9000000' + ' ignore_loglevel no_timer_check' + ' printk.time=1 rd_NO_PLYMOUTH' + ' console=ttyAMA0'), + }, + 'ppc64': + {'checksum': ('7c3528b85a3df4b2306e892199a9e1e4' + '3f991c506f2cc390dc4efa2026ad2f58')}, + 's390x': + {'checksum': ('4caaab5a434fd4d1079149a072fdc789' + '1e354f834d355069ca982fdcaf5a122d')}, + }, + '32': { + 'aarch64': + {'checksum': ('b367755c664a2d7a26955bbfff985855' + 'adfa2ca15e908baf15b4b176d68d3967'), + 'pxeboot_url': ('http://dl.fedoraproject.org/pub/fedora/linux/' + 'releases/32/Server/aarch64/os/images/' + 'pxeboot/'), + 'kernel_params': ('root=UUID=3df75b65-be8d-4db4-8655-' + '14d95c0e90c5 ro no_timer_check net.ifnames=0' + ' console=tty1 console=ttyS0,115200n8'), + }, + }, + '33': { + 'aarch64': + {'checksum': ('e7f75cdfd523fe5ac2ca9eeece68edc1' + 'a81f386a17f969c1d1c7c87031008a6b'), + 'pxeboot_url': ('http://dl.fedoraproject.org/pub/fedora/linux/' + 'releases/33/Server/aarch64/os/images/' + 'pxeboot/'), + 'kernel_params': ('root=UUID=d20b3ffa-6397-4a63-a734-' + '1126a0208f8a ro no_timer_check net.ifnames=0' + ' console=tty1 console=ttyS0,115200n8' + ' console=tty0'), + }, + }, + } + } + + def __init__(self, name, version, arch): + self.name = name + self.version = version + self.arch = arch + try: + info = self.KNOWN_DISTROS.get(name).get(version).get(arch) + except AttributeError: + # Unknown distro + info = None + self._info = info or {} + + @property + def checksum(self): + """Gets the cloud-image file checksum""" + return self._info.get('checksum', None) + + @checksum.setter + def checksum(self, value): + self._info['checksum'] = value + + @property + def pxeboot_url(self): + """Gets the repository url where pxeboot files can be found""" + return self._info.get('pxeboot_url', None) + + @property + def default_kernel_params(self): + """Gets the default kernel parameters""" + return self._info.get('kernel_params', None) + + +class LinuxTest(LinuxSSHMixIn, QemuSystemTest): + """Facilitates having a cloud-image Linux based available. + + For tests that intend to interact with guests, this is a better choice + to start with than the more vanilla `QemuSystemTest` class. + """ + + distro = None + username = 'root' + password = 'password' + smp = '2' + memory = '1024' + + def _set_distro(self): + distro_name = self.params.get( + 'distro', + default=self._get_unique_tag_val('distro')) + if not distro_name: + distro_name = 'fedora' + + distro_version = self.params.get( + 'distro_version', + default=self._get_unique_tag_val('distro_version')) + if not distro_version: + distro_version = '31' + + self.distro = LinuxDistro(distro_name, distro_version, self.arch) + + # The distro checksum behaves differently than distro name and + # version. First, it does not respect a tag with the same + # name, given that it's not expected to be used for filtering + # (distro name versions are the natural choice). Second, the + # order of precedence is: parameter, attribute and then value + # from KNOWN_DISTROS. + distro_checksum = self.params.get('distro_checksum', + default=None) + if distro_checksum: + self.distro.checksum = distro_checksum + + def setUp(self, ssh_pubkey=None, network_device_type='virtio-net'): + super().setUp() + self.require_netdev('user') + self._set_distro() + self.vm.add_args('-smp', self.smp) + self.vm.add_args('-m', self.memory) + # The following network device allows for SSH connections + self.vm.add_args('-netdev', 'user,id=vnet,hostfwd=:127.0.0.1:0-:22', + '-device', '%s,netdev=vnet' % network_device_type) + self.set_up_boot() + if ssh_pubkey is None: + ssh_pubkey, self.ssh_key = self.set_up_existing_ssh_keys() + self.set_up_cloudinit(ssh_pubkey) + + def set_up_existing_ssh_keys(self): + ssh_public_key = os.path.join(SOURCE_DIR, 'tests', 'keys', 'id_rsa.pub') + source_private_key = os.path.join(SOURCE_DIR, 'tests', 'keys', 'id_rsa') + ssh_dir = os.path.join(self.workdir, '.ssh') + os.mkdir(ssh_dir, mode=0o700) + ssh_private_key = os.path.join(ssh_dir, + os.path.basename(source_private_key)) + shutil.copyfile(source_private_key, ssh_private_key) + os.chmod(ssh_private_key, 0o600) + return (ssh_public_key, ssh_private_key) + + def download_boot(self): + # Set the qemu-img binary. + # If none is available, the test will cancel. + vmimage.QEMU_IMG = super().get_qemu_img() + + self.log.info('Downloading/preparing boot image') + # Fedora 31 only provides ppc64le images + image_arch = self.arch + if self.distro.name == 'fedora': + if image_arch == 'ppc64': + image_arch = 'ppc64le' + + try: + boot = vmimage.get( + self.distro.name, arch=image_arch, version=self.distro.version, + checksum=self.distro.checksum, + algorithm='sha256', + cache_dir=self.cache_dirs[0], + snapshot_dir=self.workdir) + except: + self.cancel('Failed to download/prepare boot image') + return boot.path + + def prepare_cloudinit(self, ssh_pubkey=None): + self.log.info('Preparing cloudinit image') + try: + cloudinit_iso = os.path.join(self.workdir, 'cloudinit.iso') + pubkey_content = None + if ssh_pubkey: + with open(ssh_pubkey) as pubkey: + pubkey_content = pubkey.read() + cloudinit.iso(cloudinit_iso, self.name, + username=self.username, + password=self.password, + # QEMU's hard coded usermode router address + phone_home_host='10.0.2.2', + phone_home_port=self.phone_server.server_port, + authorized_key=pubkey_content) + except Exception: + self.cancel('Failed to prepare the cloudinit image') + return cloudinit_iso + + def set_up_boot(self): + path = self.download_boot() + self.vm.add_args('-drive', 'file=%s' % path) + + def set_up_cloudinit(self, ssh_pubkey=None): + self.phone_server = cloudinit.PhoneHomeServer(('0.0.0.0', 0), + self.name) + cloudinit_iso = self.prepare_cloudinit(ssh_pubkey) + self.vm.add_args('-drive', 'file=%s,format=raw' % cloudinit_iso) + + def launch_and_wait(self, set_up_ssh_connection=True): + self.vm.set_console() + self.vm.launch() + console_drainer = datadrainer.LineLogger(self.vm.console_socket.fileno(), + logger=self.log.getChild('console')) + console_drainer.start() + self.log.info('VM launched, waiting for boot confirmation from guest') + while not self.phone_server.instance_phoned_back: + self.phone_server.handle_request() + + if set_up_ssh_connection: + self.log.info('Setting up the SSH connection') + self.ssh_connect(self.username, self.ssh_key) diff --git a/tests/avocado/boot_linux.py b/tests/avocado/boot_linux.py index cdce4cbcba..a029ef4ad1 100644 --- a/tests/avocado/boot_linux.py +++ b/tests/avocado/boot_linux.py @@ -10,7 +10,8 @@ import os -from avocado_qemu import LinuxTest, BUILD_DIR +from avocado_qemu.linuxtest import LinuxTest +from avocado_qemu import BUILD_DIR from avocado import skipUnless diff --git a/tests/avocado/boot_xen.py b/tests/avocado/boot_xen.py index fc2faeedb5..f29bc58b9e 100644 --- a/tests/avocado/boot_xen.py +++ b/tests/avocado/boot_xen.py @@ -17,9 +17,14 @@ from avocado_qemu import wait_for_console_pattern from boot_linux_console import LinuxKernelTest -class BootXenBase(LinuxKernelTest): +class BootXen(LinuxKernelTest): """ Boots a Xen hypervisor with a Linux DomU kernel. + + :avocado: tags=arch:aarch64 + :avocado: tags=accel:tcg + :avocado: tags=cpu:cortex-a57 + :avocado: tags=machine:virt """ timeout = 90 @@ -45,11 +50,10 @@ class BootXenBase(LinuxKernelTest): self.vm.set_console() - xen_command_line = self.XEN_COMMON_COMMAND_LINE self.vm.add_args('-machine', 'virtualization=on', '-m', '768', '-kernel', xen_path, - '-append', xen_command_line, + '-append', self.XEN_COMMON_COMMAND_LINE, '-device', 'guest-loader,addr=0x47000000,kernel=%s,bootargs=console=hvc0' % (kernel_path)) @@ -59,17 +63,7 @@ class BootXenBase(LinuxKernelTest): console_pattern = 'VFS: Cannot open root device' wait_for_console_pattern(self, console_pattern, "Panic on CPU 0:") - -class BootXen(BootXenBase): - def test_arm64_xen_411_and_dom0(self): - """ - :avocado: tags=arch:aarch64 - :avocado: tags=accel:tcg - :avocado: tags=cpu:cortex-a57 - :avocado: tags=machine:virt - """ - # archive of file from https://deb.debian.org/debian/pool/main/x/xen/ xen_url = ('https://fileserver.linaro.org/s/JSsewXGZ6mqxPr5/' 'download?path=%2F&files=' @@ -81,13 +75,6 @@ class BootXen(BootXenBase): self.launch_xen(xen_path) def test_arm64_xen_414_and_dom0(self): - """ - :avocado: tags=arch:aarch64 - :avocado: tags=accel:tcg - :avocado: tags=cpu:cortex-a57 - :avocado: tags=machine:virt - """ - # archive of file from https://deb.debian.org/debian/pool/main/x/xen/ xen_url = ('https://fileserver.linaro.org/s/JSsewXGZ6mqxPr5/' 'download?path=%2F&files=' @@ -99,13 +86,6 @@ class BootXen(BootXenBase): self.launch_xen(xen_path) def test_arm64_xen_415_and_dom0(self): - """ - :avocado: tags=arch:aarch64 - :avocado: tags=accel:tcg - :avocado: tags=cpu:cortex-a57 - :avocado: tags=machine:virt - """ - xen_url = ('https://fileserver.linaro.org/' 's/JSsewXGZ6mqxPr5/download' '?path=%2F&files=xen-upstream-4.15-unstable.deb') diff --git a/tests/avocado/hotplug_blk.py b/tests/avocado/hotplug_blk.py index 5dc30f6616..d55ded1c1d 100644 --- a/tests/avocado/hotplug_blk.py +++ b/tests/avocado/hotplug_blk.py @@ -9,7 +9,7 @@ import time -from avocado_qemu import LinuxTest +from avocado_qemu.linuxtest import LinuxTest class HotPlug(LinuxTest): diff --git a/tests/avocado/hotplug_cpu.py b/tests/avocado/hotplug_cpu.py index 292bb43e4d..342c838539 100644 --- a/tests/avocado/hotplug_cpu.py +++ b/tests/avocado/hotplug_cpu.py @@ -8,7 +8,7 @@ # This work is licensed under the terms of the GNU GPL, version 2 or # later. See the COPYING file in the top-level directory. -from avocado_qemu import LinuxTest +from avocado_qemu.linuxtest import LinuxTest class HotPlugCPU(LinuxTest): diff --git a/tests/avocado/intel_iommu.py b/tests/avocado/intel_iommu.py index 09e694bd40..008f214397 100644 --- a/tests/avocado/intel_iommu.py +++ b/tests/avocado/intel_iommu.py @@ -10,7 +10,7 @@ import os from avocado import skipUnless -from avocado_qemu import LinuxTest +from avocado_qemu.linuxtest import LinuxTest @skipUnless(os.getenv('QEMU_TEST_FLAKY_TESTS'), 'Test is unstable on GitLab') diff --git a/tests/avocado/machine_aspeed.py b/tests/avocado/machine_aspeed.py index 29e6b388a9..f8e263d37e 100644 --- a/tests/avocado/machine_aspeed.py +++ b/tests/avocado/machine_aspeed.py @@ -87,7 +87,7 @@ class AST1030Machine(QemuSystemTest): class AST2x00Machine(QemuSystemTest): - timeout = 90 + timeout = 180 def wait_for_console_pattern(self, success_message, vm=None): wait_for_console_pattern(self, success_message, diff --git a/tests/avocado/machine_sparc_leon3.py b/tests/avocado/machine_sparc_leon3.py deleted file mode 100644 index e61b223185..0000000000 --- a/tests/avocado/machine_sparc_leon3.py +++ /dev/null @@ -1,37 +0,0 @@ -# Functional test that boots a Leon3 machine and checks its serial console. -# -# Copyright (c) Philippe Mathieu-Daudé <f4bug@amsat.org> -# -# This work is licensed under the terms of the GNU GPL, version 2 or -# later. See the COPYING file in the top-level directory. - -from avocado_qemu import QemuSystemTest -from avocado_qemu import wait_for_console_pattern -from avocado import skip - - -class Leon3Machine(QemuSystemTest): - - timeout = 60 - - @skip("Test currently broken") - # A Window Underflow exception occurs before booting the kernel, - # and QEMU exit calling cpu_abort(), which makes this test to fail. - def test_leon3_helenos_uimage(self): - """ - :avocado: tags=arch:sparc - :avocado: tags=machine:leon3_generic - :avocado: tags=binfmt:uimage - """ - kernel_url = ('http://www.helenos.org/releases/' - 'HelenOS-0.6.0-sparc32-leon3.bin') - kernel_hash = 'a88c9cfdb8430c66650e5290a08765f9bf049a30' - kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) - - self.vm.set_console() - self.vm.add_args('-kernel', kernel_path) - - self.vm.launch() - - wait_for_console_pattern(self, 'Copyright (c) 2001-2014 HelenOS project') - wait_for_console_pattern(self, 'Booting the kernel ...') diff --git a/tests/avocado/mem-addr-space-check.py b/tests/avocado/mem-addr-space-check.py index 85541ea051..d3974599f4 100644 --- a/tests/avocado/mem-addr-space-check.py +++ b/tests/avocado/mem-addr-space-check.py @@ -9,7 +9,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later from avocado_qemu import QemuSystemTest -import signal import time class MemAddrCheck(QemuSystemTest): diff --git a/tests/avocado/replay_linux.py b/tests/avocado/replay_linux.py index f3a43dc98c..b4673261ce 100644 --- a/tests/avocado/replay_linux.py +++ b/tests/avocado/replay_linux.py @@ -19,7 +19,7 @@ from avocado.utils import network from avocado.utils import vmimage from avocado.utils import datadrainer from avocado.utils.path import find_command -from avocado_qemu import LinuxTest +from avocado_qemu.linuxtest import LinuxTest class ReplayLinux(LinuxTest): """ diff --git a/tests/avocado/smmu.py b/tests/avocado/smmu.py index 4ebfa7128c..aadda71e4b 100644 --- a/tests/avocado/smmu.py +++ b/tests/avocado/smmu.py @@ -10,7 +10,8 @@ import os from avocado import skipUnless -from avocado_qemu import LinuxTest, BUILD_DIR +from avocado_qemu import BUILD_DIR +from avocado_qemu.linuxtest import LinuxTest @skipUnless(os.getenv('QEMU_TEST_FLAKY_TESTS'), 'Test is unstable on GitLab') diff --git a/tests/avocado/virtiofs_submounts.py.data/cleanup.sh b/tests/avocado/virtiofs_submounts.py.data/cleanup.sh deleted file mode 100644 index 2a6579a0fe..0000000000 --- a/tests/avocado/virtiofs_submounts.py.data/cleanup.sh +++ /dev/null @@ -1,46 +0,0 @@ -#!/bin/bash - -function print_usage() -{ - if [ -n "$2" ]; then - echo "Error: $2" - echo - fi - echo "Usage: $1 <scratch dir>" -} - -scratch_dir=$1 -if [ -z "$scratch_dir" ]; then - print_usage "$0" 'Scratch dir not given' >&2 - exit 1 -fi - -cd "$scratch_dir/share" || exit 1 -mps=(mnt*) -mp_i=0 -for mp in "${mps[@]}"; do - mp_i=$((mp_i + 1)) - printf "Unmounting %i/%i...\r" "$mp_i" "${#mps[@]}" - - sudo umount -R "$mp" - rm -rf "$mp" -done -echo - -rm some-file -cd .. -rmdir share - -imgs=(fs*.img) -img_i=0 -for img in "${imgs[@]}"; do - img_i=$((img_i + 1)) - printf "Detaching and deleting %i/%i...\r" "$img_i" "${#imgs[@]}" - - dev=$(losetup -j "$img" | sed -e 's/:.*//') - sudo losetup -d "$dev" - rm -f "$img" -done -echo - -echo 'Done.' diff --git a/tests/avocado/virtiofs_submounts.py.data/guest-cleanup.sh b/tests/avocado/virtiofs_submounts.py.data/guest-cleanup.sh deleted file mode 100644 index 729cb2d1a5..0000000000 --- a/tests/avocado/virtiofs_submounts.py.data/guest-cleanup.sh +++ /dev/null @@ -1,30 +0,0 @@ -#!/bin/bash - -function print_usage() -{ - if [ -n "$2" ]; then - echo "Error: $2" - echo - fi - echo "Usage: $1 <scratch dir>" -} - -scratch_dir=$1 -if [ -z "$scratch_dir" ]; then - print_usage "$0" 'Scratch dir not given' >&2 - exit 1 -fi - -cd "$scratch_dir/share" || exit 1 - -mps=(mnt*) -mp_i=0 -for mp in "${mps[@]}"; do - mp_i=$((mp_i + 1)) - printf "Unmounting %i/%i...\r" "$mp_i" "${#mps[@]}" - - sudo umount -R "$mp" -done -echo - -echo 'Done.' diff --git a/tests/avocado/virtiofs_submounts.py.data/guest.sh b/tests/avocado/virtiofs_submounts.py.data/guest.sh deleted file mode 100644 index 59ba40fde1..0000000000 --- a/tests/avocado/virtiofs_submounts.py.data/guest.sh +++ /dev/null @@ -1,138 +0,0 @@ -#!/bin/bash - -function print_usage() -{ - if [ -n "$2" ]; then - echo "Error: $2" - echo - fi - echo "Usage: $1 <shared dir>" - echo '(The shared directory is the "share" directory in the scratch' \ - 'directory)' -} - -shared_dir=$1 -if [ -z "$shared_dir" ]; then - print_usage "$0" 'Shared dir not given' >&2 - exit 1 -fi - -cd "$shared_dir" - -# FIXME: This should not be necessary, but it is. In order for all -# submounts to be proper mount points, we need to visit them. -# (Before we visit them, they will not be auto-mounted, and so just -# appear as normal directories, with the catch that their st_ino will -# be the st_ino of the filesystem they host, while the st_dev will -# still be the st_dev of the parent.) -# `find` does not work, because it will refuse to touch the mount -# points as long as they are not mounted; their st_dev being shared -# with the parent and st_ino just being the root node's inode ID -# will practically ensure that this node exists elsewhere on the -# filesystem, and `find` is required to recognize loops and not to -# follow them. -# Thus, we have to manually visit all nodes first. - -mnt_i=0 - -function recursively_visit() -{ - pushd "$1" >/dev/null - for entry in *; do - if [[ "$entry" == mnt* ]]; then - mnt_i=$((mnt_i + 1)) - printf "Triggering auto-mount $mnt_i...\r" - fi - - if [ -d "$entry" ]; then - recursively_visit "$entry" - fi - done - popd >/dev/null -} - -recursively_visit . -echo - - -if [ -n "$(find -name not-mounted)" ]; then - echo "Error: not-mounted files visible on mount points:" >&2 - find -name not-mounted >&2 - exit 1 -fi - -if [ ! -f some-file -o "$(cat some-file)" != 'root' ]; then - echo "Error: Bad file in the share root" >&2 - exit 1 -fi - -shopt -s nullglob - -function check_submounts() -{ - local base_path=$1 - - for mp in mnt*; do - printf "Checking submount %i...\r" "$((${#devs[@]} + 1))" - - mp_i=$(echo "$mp" | sed -e 's/mnt//') - dev=$(stat -c '%D' "$mp") - - if [ -n "${devs[mp_i]}" ]; then - echo "Error: $mp encountered twice" >&2 - exit 1 - fi - devs[mp_i]=$dev - - pushd "$mp" >/dev/null - path="$base_path$mp" - while true; do - expected_content="$(printf '%s\n%s\n' "$mp_i" "$path")" - if [ ! -f some-file ]; then - echo "Error: $PWD/some-file does not exist" >&2 - exit 1 - fi - - if [ "$(cat some-file)" != "$expected_content" ]; then - echo "Error: Bad content in $PWD/some-file:" >&2 - echo '--- found ---' - cat some-file - echo '--- expected ---' - echo "$expected_content" - exit 1 - fi - if [ "$(stat -c '%D' some-file)" != "$dev" ]; then - echo "Error: $PWD/some-file has the wrong device ID" >&2 - exit 1 - fi - - if [ -d sub ]; then - if [ "$(stat -c '%D' sub)" != "$dev" ]; then - echo "Error: $PWD/some-file has the wrong device ID" >&2 - exit 1 - fi - cd sub - path="$path/sub" - else - if [ -n "$(echo mnt*)" ]; then - check_submounts "$path/" - fi - break - fi - done - popd >/dev/null - done -} - -root_dev=$(stat -c '%D' some-file) -devs=() -check_submounts '' -echo - -reused_devs=$(echo "$root_dev ${devs[@]}" | tr ' ' '\n' | sort | uniq -d) -if [ -n "$reused_devs" ]; then - echo "Error: Reused device IDs: $reused_devs" >&2 - exit 1 -fi - -echo "Test passed for ${#devs[@]} submounts." diff --git a/tests/avocado/virtiofs_submounts.py.data/host.sh b/tests/avocado/virtiofs_submounts.py.data/host.sh deleted file mode 100644 index d8a9afebdb..0000000000 --- a/tests/avocado/virtiofs_submounts.py.data/host.sh +++ /dev/null @@ -1,127 +0,0 @@ -#!/bin/bash - -mount_count=128 - -function print_usage() -{ - if [ -n "$2" ]; then - echo "Error: $2" - echo - fi - echo "Usage: $1 <scratch dir> [seed]" - echo "(If no seed is given, it will be randomly generated.)" -} - -scratch_dir=$1 -if [ -z "$scratch_dir" ]; then - print_usage "$0" 'No scratch dir given' >&2 - exit 1 -fi - -if [ ! -d "$scratch_dir" ]; then - print_usage "$0" "$scratch_dir is not a directory" >&2 - exit 1 -fi - -seed=$2 -if [ -z "$seed" ]; then - seed=$RANDOM -fi -RANDOM=$seed - -echo "Seed: $seed" - -set -e -shopt -s nullglob - -cd "$scratch_dir" -if [ -d share ]; then - echo 'Error: This directory seems to be in use already' >&2 - exit 1 -fi - -for ((i = 0; i < $mount_count; i++)); do - printf "Setting up fs %i/%i...\r" "$((i + 1))" "$mount_count" - - rm -f fs$i.img - truncate -s 512M fs$i.img - mkfs.xfs -q fs$i.img - devs[i]=$(sudo losetup -f --show fs$i.img) -done -echo - -top_level_mounts=$((RANDOM % mount_count + 1)) - -mkdir -p share -echo 'root' > share/some-file - -for ((i = 0; i < $top_level_mounts; i++)); do - printf "Mounting fs %i/%i...\r" "$((i + 1))" "$mount_count" - - mkdir -p share/mnt$i - touch share/mnt$i/not-mounted - sudo mount "${devs[i]}" share/mnt$i - sudo chown "$(id -u):$(id -g)" share/mnt$i - - pushd share/mnt$i >/dev/null - path=mnt$i - nesting=$((RANDOM % 4)) - for ((j = 0; j < $nesting; j++)); do - cat > some-file <<EOF -$i -$path -EOF - mkdir sub - cd sub - path="$path/sub" - done -cat > some-file <<EOF -$i -$path -EOF - popd >/dev/null -done - -for ((; i < $mount_count; i++)); do - printf "Mounting fs %i/%i...\r" "$((i + 1))" "$mount_count" - - mp_i=$((i % top_level_mounts)) - - pushd share/mnt$mp_i >/dev/null - path=mnt$mp_i - while true; do - sub_mp="$(echo mnt*)" - if cd sub 2>/dev/null; then - path="$path/sub" - elif [ -n "$sub_mp" ] && cd "$sub_mp" 2>/dev/null; then - path="$path/$sub_mp" - else - break - fi - done - mkdir mnt$i - touch mnt$i/not-mounted - sudo mount "${devs[i]}" mnt$i - sudo chown "$(id -u):$(id -g)" mnt$i - - cd mnt$i - path="$path/mnt$i" - nesting=$((RANDOM % 4)) - for ((j = 0; j < $nesting; j++)); do - cat > some-file <<EOF -$i -$path -EOF - mkdir sub - cd sub - path="$path/sub" - done - cat > some-file <<EOF -$i -$path -EOF - popd >/dev/null -done -echo - -echo 'Done.' diff --git a/tests/data/acpi/aarch64/virt/DSDT b/tests/data/acpi/aarch64/virt/DSDT index c475039907..36d3e5d5a5 100644 --- a/tests/data/acpi/aarch64/virt/DSDT +++ b/tests/data/acpi/aarch64/virt/DSDT Binary files differdiff --git a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt index aee6ba017c..e6154d0355 100644 --- a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt +++ b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt Binary files differdiff --git a/tests/data/acpi/aarch64/virt/DSDT.memhp b/tests/data/acpi/aarch64/virt/DSDT.memhp index bae36cdd39..33f011d6b6 100644 --- a/tests/data/acpi/aarch64/virt/DSDT.memhp +++ b/tests/data/acpi/aarch64/virt/DSDT.memhp Binary files differdiff --git a/tests/data/acpi/aarch64/virt/DSDT.pxb b/tests/data/acpi/aarch64/virt/DSDT.pxb index fbd78f44c4..c0fdc6e9c1 100644 --- a/tests/data/acpi/aarch64/virt/DSDT.pxb +++ b/tests/data/acpi/aarch64/virt/DSDT.pxb Binary files differdiff --git a/tests/data/acpi/aarch64/virt/DSDT.topology b/tests/data/acpi/aarch64/virt/DSDT.topology index 501314c91b..029d03eecc 100644 --- a/tests/data/acpi/aarch64/virt/DSDT.topology +++ b/tests/data/acpi/aarch64/virt/DSDT.topology Binary files differdiff --git a/tests/data/acpi/riscv64/virt/APIC b/tests/data/acpi/riscv64/virt/APIC new file mode 100644 index 0000000000..66a25dfd2d --- /dev/null +++ b/tests/data/acpi/riscv64/virt/APIC Binary files differdiff --git a/tests/data/acpi/riscv64/virt/DSDT b/tests/data/acpi/riscv64/virt/DSDT new file mode 100644 index 0000000000..6a33f5647d --- /dev/null +++ b/tests/data/acpi/riscv64/virt/DSDT Binary files differdiff --git a/tests/data/acpi/riscv64/virt/FACP b/tests/data/acpi/riscv64/virt/FACP new file mode 100644 index 0000000000..a5276b65ea --- /dev/null +++ b/tests/data/acpi/riscv64/virt/FACP Binary files differdiff --git a/tests/data/acpi/riscv64/virt/MCFG b/tests/data/acpi/riscv64/virt/MCFG new file mode 100644 index 0000000000..37eb923a93 --- /dev/null +++ b/tests/data/acpi/riscv64/virt/MCFG Binary files differdiff --git a/tests/data/acpi/riscv64/virt/RHCT b/tests/data/acpi/riscv64/virt/RHCT new file mode 100644 index 0000000000..4f231735ab --- /dev/null +++ b/tests/data/acpi/riscv64/virt/RHCT Binary files differdiff --git a/tests/data/acpi/riscv64/virt/SPCR b/tests/data/acpi/riscv64/virt/SPCR new file mode 100644 index 0000000000..4da9daf65f --- /dev/null +++ b/tests/data/acpi/riscv64/virt/SPCR Binary files differdiff --git a/tests/data/acpi/x86/microvm/DSDT.pcie b/tests/data/acpi/x86/microvm/DSDT.pcie index 765f14ef3d..8eacd21d6e 100644 --- a/tests/data/acpi/x86/microvm/DSDT.pcie +++ b/tests/data/acpi/x86/microvm/DSDT.pcie Binary files differdiff --git a/tests/lcitool/libvirt-ci b/tests/lcitool/libvirt-ci -Subproject 0e9490cebc726ef772b6c9e27dac32e7ae99f9b +Subproject 789b4601bce4e01f43fdb6ad4ce5ab4e4667444 diff --git a/tests/plugin/inline.c b/tests/plugin/inline.c index cd63827b7d..73dde99578 100644 --- a/tests/plugin/inline.c +++ b/tests/plugin/inline.c @@ -71,10 +71,12 @@ static void stats_insn(void) const uint64_t cond_track_left = qemu_plugin_u64_sum(insn_cond_track_count); const uint64_t conditional = cond_num_trigger * cond_trigger_limit + cond_track_left; - printf("insn: %" PRIu64 "\n", expected); - printf("insn: %" PRIu64 " (per vcpu)\n", per_vcpu); - printf("insn: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu); - printf("insn: %" PRIu64 " (cond cb)\n", conditional); + g_autoptr(GString) stats = g_string_new(""); + g_string_append_printf(stats, "insn: %" PRIu64 "\n", expected); + g_string_append_printf(stats, "insn: %" PRIu64 " (per vcpu)\n", per_vcpu); + g_string_append_printf(stats, "insn: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu); + g_string_append_printf(stats, "insn: %" PRIu64 " (cond cb)\n", conditional); + qemu_plugin_outs(stats->str); g_assert(expected > 0); g_assert(per_vcpu == expected); g_assert(inl_per_vcpu == expected); @@ -91,10 +93,12 @@ static void stats_tb(void) const uint64_t cond_track_left = qemu_plugin_u64_sum(tb_cond_track_count); const uint64_t conditional = cond_num_trigger * cond_trigger_limit + cond_track_left; - printf("tb: %" PRIu64 "\n", expected); - printf("tb: %" PRIu64 " (per vcpu)\n", per_vcpu); - printf("tb: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu); - printf("tb: %" PRIu64 " (conditional cb)\n", conditional); + g_autoptr(GString) stats = g_string_new(""); + g_string_append_printf(stats, "tb: %" PRIu64 "\n", expected); + g_string_append_printf(stats, "tb: %" PRIu64 " (per vcpu)\n", per_vcpu); + g_string_append_printf(stats, "tb: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu); + g_string_append_printf(stats, "tb: %" PRIu64 " (conditional cb)\n", conditional); + qemu_plugin_outs(stats->str); g_assert(expected > 0); g_assert(per_vcpu == expected); g_assert(inl_per_vcpu == expected); @@ -107,9 +111,11 @@ static void stats_mem(void) const uint64_t per_vcpu = qemu_plugin_u64_sum(count_mem); const uint64_t inl_per_vcpu = qemu_plugin_u64_sum(count_mem_inline); - printf("mem: %" PRIu64 "\n", expected); - printf("mem: %" PRIu64 " (per vcpu)\n", per_vcpu); - printf("mem: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu); + g_autoptr(GString) stats = g_string_new(""); + g_string_append_printf(stats, "mem: %" PRIu64 "\n", expected); + g_string_append_printf(stats, "mem: %" PRIu64 " (per vcpu)\n", per_vcpu); + g_string_append_printf(stats, "mem: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu); + qemu_plugin_outs(stats->str); g_assert(expected > 0); g_assert(per_vcpu == expected); g_assert(inl_per_vcpu == expected); @@ -118,6 +124,7 @@ static void stats_mem(void) static void plugin_exit(qemu_plugin_id_t id, void *udata) { const unsigned int num_cpus = qemu_plugin_num_vcpus(); + g_autoptr(GString) stats = g_string_new(""); g_assert(num_cpus == max_cpu_index + 1); for (int i = 0; i < num_cpus ; ++i) { @@ -135,20 +142,21 @@ static void plugin_exit(qemu_plugin_id_t id, void *udata) qemu_plugin_u64_get(insn_cond_num_trigger, i); const uint64_t insn_cond_left = qemu_plugin_u64_get(insn_cond_track_count, i); - printf("cpu %d: tb (%" PRIu64 ", %" PRIu64 - ", %" PRIu64 " * %" PRIu64 " + %" PRIu64 - ") | " - "insn (%" PRIu64 ", %" PRIu64 - ", %" PRIu64 " * %" PRIu64 " + %" PRIu64 - ") | " - "mem (%" PRIu64 ", %" PRIu64 ")" - "\n", - i, - tb, tb_inline, - tb_cond_trigger, cond_trigger_limit, tb_cond_left, - insn, insn_inline, - insn_cond_trigger, cond_trigger_limit, insn_cond_left, - mem, mem_inline); + g_string_printf(stats, "cpu %d: tb (%" PRIu64 ", %" PRIu64 + ", %" PRIu64 " * %" PRIu64 " + %" PRIu64 + ") | " + "insn (%" PRIu64 ", %" PRIu64 + ", %" PRIu64 " * %" PRIu64 " + %" PRIu64 + ") | " + "mem (%" PRIu64 ", %" PRIu64 ")" + "\n", + i, + tb, tb_inline, + tb_cond_trigger, cond_trigger_limit, tb_cond_left, + insn, insn_inline, + insn_cond_trigger, cond_trigger_limit, insn_cond_left, + mem, mem_inline); + qemu_plugin_outs(stats->str); g_assert(tb == tb_inline); g_assert(insn == insn_inline); g_assert(mem == mem_inline); diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c index f4c4704bab..36e5c0adde 100644 --- a/tests/qtest/bios-tables-test.c +++ b/tests/qtest/bios-tables-test.c @@ -267,15 +267,6 @@ static void dump_aml_files(test_data *data, bool rebuild) data->arch, data->machine, sdt->aml, ext); - /* - * To keep test cases not failing before the DATA files are moved to - * ${arch}/${machine} folder, add this check as well. - */ - if (!g_file_test(aml_file, G_FILE_TEST_EXISTS)) { - aml_file = g_strdup_printf("%s/%s/%.4s%s", data_dir, - data->machine, sdt->aml, ext); - } - if (!g_file_test(aml_file, G_FILE_TEST_EXISTS) && sdt->aml_len == exp_sdt->aml_len && !memcmp(sdt->aml, exp_sdt->aml, sdt->aml_len)) { @@ -412,11 +403,6 @@ static GArray *load_expected_aml(test_data *data) try_again: aml_file = g_strdup_printf("%s/%s/%s/%.4s%s", data_dir, data->arch, data->machine, sdt->aml, ext); - if (!g_file_test(aml_file, G_FILE_TEST_EXISTS)) { - aml_file = g_strdup_printf("%s/%s/%.4s%s", data_dir, data->machine, - sdt->aml, ext); - } - if (verbosity_level >= 2) { fprintf(stderr, "Looking for expected file '%s'\n", aml_file); } @@ -1977,6 +1963,28 @@ static void test_acpi_microvm_acpi_erst(void) } #endif /* CONFIG_POSIX */ +static void test_acpi_riscv64_virt_tcg(void) +{ + test_data data = { + .machine = "virt", + .arch = "riscv64", + .tcg_only = true, + .uefi_fl1 = "pc-bios/edk2-riscv-code.fd", + .uefi_fl2 = "pc-bios/edk2-riscv-vars.fd", + .cd = "tests/data/uefi-boot-images/bios-tables-test.riscv64.iso.qcow2", + .ram_start = 0x80000000ULL, + .scan_len = 128ULL * 1024 * 1024, + }; + + /* + * RHCT will have ISA string encoded. To reduce the effort + * of updating expected AML file for any new default ISA extension, + * use the profile rva22s64. + */ + test_acpi_one("-cpu rva22s64 ", &data); + free_test_data(&data); +} + static void test_acpi_aarch64_virt_tcg(void) { test_data data = { @@ -2455,6 +2463,10 @@ int main(int argc, char *argv[]) qtest_add_func("acpi/virt/viot", test_acpi_aarch64_virt_viot); } } + } else if (strcmp(arch, "riscv64") == 0) { + if (has_tcg && qtest_has_device("virtio-blk-pci")) { + qtest_add_func("acpi/virt", test_acpi_riscv64_virt_tcg); + } } ret = g_test_run(); boot_sector_cleanup(disk); diff --git a/tests/qtest/fuzz/generic_fuzz.c b/tests/qtest/fuzz/generic_fuzz.c index ec842e03c5..d107a496da 100644 --- a/tests/qtest/fuzz/generic_fuzz.c +++ b/tests/qtest/fuzz/generic_fuzz.c @@ -11,6 +11,7 @@ */ #include "qemu/osdep.h" +#include "qemu/range.h" #include <wordexp.h> @@ -211,7 +212,7 @@ void fuzz_dma_read_cb(size_t addr, size_t len, MemoryRegion *mr) i < dma_regions->len && (avoid_double_fetches || qtest_log_enabled); ++i) { region = g_array_index(dma_regions, address_range, i); - if (addr < region.addr + region.size && addr + len > region.addr) { + if (ranges_overlap(addr, len, region.addr, region.size)) { double_fetch = true; if (addr < region.addr && avoid_double_fetches) { diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index 6508bfb1a2..ff9200f882 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -1,6 +1,6 @@ slow_qtests = { 'aspeed_smc-test': 360, - 'bios-tables-test' : 610, + 'bios-tables-test' : 910, 'cdrom-test' : 610, 'device-introspect-test' : 720, 'migration-test' : 480, diff --git a/tests/tcg/aarch64/gdbstub/test-mte.py b/tests/tcg/aarch64/gdbstub/test-mte.py index 2db0663c1a..66f9c25f8a 100644 --- a/tests/tcg/aarch64/gdbstub/test-mte.py +++ b/tests/tcg/aarch64/gdbstub/test-mte.py @@ -18,7 +18,7 @@ import re from test_gdbstub import main, report -PATTERN_0 = "Memory tags for address 0x[0-9a-f]+ match \(0x[0-9a-f]+\)." +PATTERN_0 = "Memory tags for address 0x[0-9a-f]+ match \\(0x[0-9a-f]+\\)." PATTERN_1 = ".*(0x[0-9a-f]+)" diff --git a/tests/vm/generated/freebsd.json b/tests/vm/generated/freebsd.json index 2d5895ebed..2a361cecd0 100644 --- a/tests/vm/generated/freebsd.json +++ b/tests/vm/generated/freebsd.json @@ -51,13 +51,13 @@ "pixman", "pkgconf", "png", - "py39-numpy", - "py39-pillow", - "py39-pip", - "py39-sphinx", - "py39-sphinx_rtd_theme", - "py39-tomli", - "py39-yaml", + "py311-numpy", + "py311-pillow", + "py311-pip", + "py311-sphinx", + "py311-sphinx_rtd_theme", + "py311-tomli", + "py311-yaml", "python3", "rpm2cpio", "sdl2", diff --git a/ui/clipboard.c b/ui/clipboard.c index 4264884a6c..132086eb13 100644 --- a/ui/clipboard.c +++ b/ui/clipboard.c @@ -155,6 +155,8 @@ void qemu_clipboard_reset_serial(void) QemuClipboardNotify notify = { .type = QEMU_CLIPBOARD_RESET_SERIAL }; int i; + trace_clipboard_reset_serial(); + for (i = 0; i < QEMU_CLIPBOARD_SELECTION__COUNT; i++) { QemuClipboardInfo *info = qemu_clipboard_info(i); if (info) { diff --git a/ui/cursor.c b/ui/cursor.c index 29717b3ecb..dd3853320d 100644 --- a/ui/cursor.c +++ b/ui/cursor.c @@ -232,7 +232,7 @@ void cursor_get_mono_mask(QEMUCursor *c, int transparent, uint8_t *mask) for (y = 0; y < c->height; y++) { bit = 0x80; for (x = 0; x < c->width; x++, data++) { - if ((*data & 0xff000000) != 0xff000000) { + if ((*data & 0x80000000) == 0x0) { /* Alpha < 0x80 (128) */ if (transparent != 0) { mask[x/8] |= bit; } diff --git a/ui/dbus-clipboard.c b/ui/dbus-clipboard.c index fe7fcdecb6..fbb043abca 100644 --- a/ui/dbus-clipboard.c +++ b/ui/dbus-clipboard.c @@ -141,6 +141,8 @@ dbus_clipboard_qemu_request(QemuClipboardInfo *info, const char *mimes[] = { MIME_TEXT_PLAIN_UTF8, NULL }; size_t n; + trace_dbus_clipboard_qemu_request(type); + if (type != QEMU_CLIPBOARD_TYPE_TEXT) { /* unsupported atm */ return; @@ -305,6 +307,8 @@ dbus_clipboard_grab( return DBUS_METHOD_INVOCATION_HANDLED; } + trace_dbus_clipboard_grab(arg_selection, arg_serial); + if (s >= QEMU_CLIPBOARD_SELECTION__COUNT) { g_dbus_method_invocation_return_error( invocation, diff --git a/ui/trace-events b/ui/trace-events index 69ff22955d..fb253c1666 100644 --- a/ui/trace-events +++ b/ui/trace-events @@ -130,9 +130,10 @@ xkeymap_keymap(const char *name) "keymap '%s'" # clipboard.c clipboard_check_serial(int cur, int recv, bool ok) "cur:%d recv:%d %d" +clipboard_reset_serial(void) "" # vdagent.c -vdagent_open(void) "" +vdagent_fe_open(bool fe_open) "fe_open=%d" vdagent_close(void) "" vdagent_disconnect(void) "" vdagent_send(const char *name) "msg %s" @@ -157,7 +158,9 @@ dbus_mouse_rel_motion(int dx, int dy) "dx=%d, dy=%d" dbus_touch_send_event(unsigned int kind, uint32_t num_slot, uint32_t x, uint32_t y) "kind=%u, num_slot=%u, x=%d, y=%d" dbus_update(int x, int y, int w, int h) "x=%d, y=%d, w=%d, h=%d" dbus_update_gl(int x, int y, int w, int h) "x=%d, y=%d, w=%d, h=%d" +dbus_clipboard_grab(int selection, unsigned int serial) "selection=%d serial=%u" dbus_clipboard_grab_failed(void) "" +dbus_clipboard_qemu_request(int type) "type=%d" dbus_clipboard_register(const char *bus_name) "peer %s" dbus_clipboard_unregister(const char *bus_name) "peer %s" dbus_scanout_texture(uint32_t tex_id, bool backing_y_0_top, uint32_t backing_width, uint32_t backing_height, uint32_t x, uint32_t y, uint32_t w, uint32_t h) "tex_id:%u y0top:%d back:%ux%u %u+%u-%ux%u" diff --git a/ui/vdagent.c b/ui/vdagent.c index 64d7ab245a..724eff972f 100644 --- a/ui/vdagent.c +++ b/ui/vdagent.c @@ -185,7 +185,7 @@ static void vdagent_send_msg(VDAgentChardev *vd, VDAgentMessage *msg) vdagent_send_buf(vd); } -static void vdagent_send_caps(VDAgentChardev *vd) +static void vdagent_send_caps(VDAgentChardev *vd, bool request) { g_autofree VDAgentMessage *msg = g_malloc0(sizeof(VDAgentMessage) + sizeof(VDAgentAnnounceCapabilities) + @@ -205,6 +205,7 @@ static void vdagent_send_caps(VDAgentChardev *vd) #endif } + caps->request = request; vdagent_send_msg(vd, msg); } @@ -711,7 +712,7 @@ static void vdagent_chr_recv_caps(VDAgentChardev *vd, VDAgentMessage *msg) vd->caps = caps->caps[0]; if (caps->request) { - vdagent_send_caps(vd); + vdagent_send_caps(vd, false); } if (have_mouse(vd) && vd->mouse_hs) { qemu_input_handler_activate(vd->mouse_hs); @@ -720,6 +721,8 @@ static void vdagent_chr_recv_caps(VDAgentChardev *vd, VDAgentMessage *msg) memset(vd->last_serial, 0, sizeof(vd->last_serial)); if (have_clipboard(vd) && vd->cbpeer.notifier.notify == NULL) { + qemu_clipboard_reset_serial(); + vd->cbpeer.name = "vdagent"; vd->cbpeer.notifier.notify = vdagent_clipboard_notify; vd->cbpeer.request = vdagent_clipboard_request; @@ -872,6 +875,8 @@ static void vdagent_chr_set_fe_open(struct Chardev *chr, int fe_open) { VDAgentChardev *vd = QEMU_VDAGENT_CHARDEV(chr); + trace_vdagent_fe_open(fe_open); + if (!fe_open) { trace_vdagent_close(); vdagent_disconnect(vd); @@ -881,7 +886,7 @@ static void vdagent_chr_set_fe_open(struct Chardev *chr, int fe_open) return; } - trace_vdagent_open(); + vdagent_send_caps(vd, true); } static void vdagent_chr_parse(QemuOpts *opts, ChardevBackend *backend, diff --git a/ui/vnc.h b/ui/vnc.h index 4521dc88f7..e5fa2efa3e 100644 --- a/ui/vnc.h +++ b/ui/vnc.h @@ -81,8 +81,8 @@ typedef void VncSendHextileTile(VncState *vs, /* VNC_MAX_WIDTH must be a multiple of VNC_DIRTY_PIXELS_PER_BIT. */ -#define VNC_MAX_WIDTH ROUND_UP(2560, VNC_DIRTY_PIXELS_PER_BIT) -#define VNC_MAX_HEIGHT 2048 +#define VNC_MAX_WIDTH ROUND_UP(5120, VNC_DIRTY_PIXELS_PER_BIT) +#define VNC_MAX_HEIGHT 2160 /* VNC_DIRTY_BITS is the number of bits in the dirty bitmap. */ #define VNC_DIRTY_BITS (VNC_MAX_WIDTH / VNC_DIRTY_PIXELS_PER_BIT) |