diff options
65 files changed, 2497 insertions, 222 deletions
diff --git a/accel/tcg/icount-common.c b/accel/tcg/icount-common.c index 8d3d3a7e9d..30bf8500dc 100644 --- a/accel/tcg/icount-common.c +++ b/accel/tcg/icount-common.c @@ -36,7 +36,6 @@ #include "sysemu/runstate.h" #include "hw/core/cpu.h" #include "sysemu/cpu-timers.h" -#include "sysemu/cpu-throttle.h" #include "sysemu/cpu-timers-internal.h" /* diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 7c2be89325..ff404d44f8 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -147,6 +147,14 @@ options are removed in favor of using explicit ``blockdev-create`` and ``blockdev-add`` calls. See :doc:`/interop/live-block-operations` for details. +``query-migrationthreads`` (since 9.2) +'''''''''''''''''''''''''''''''''''''' + +To be removed with no replacement, as it reports only a limited set of +threads (for example, it only reports source side of multifd threads, +without reporting any destination threads, or non-multifd source threads). +For debugging purpose, please use ``-name $VM,debug-threads=on`` instead. + Incorrectly typed ``device_add`` arguments (since 6.2) '''''''''''''''''''''''''''''''''''''''''''''''''''''' diff --git a/hw/loongarch/boot.c b/hw/loongarch/boot.c index cb668703bd..f258eefe9a 100644 --- a/hw/loongarch/boot.c +++ b/hw/loongarch/boot.c @@ -278,7 +278,7 @@ static void init_boot_rom(struct loongarch_boot_info *info, void *p) static void loongarch_direct_kernel_boot(struct loongarch_boot_info *info) { void *p, *bp; - int64_t kernel_addr = 0; + int64_t kernel_addr = VIRT_FLASH0_BASE; LoongArchCPU *lacpu; CPUState *cs; @@ -286,8 +286,7 @@ static void loongarch_direct_kernel_boot(struct loongarch_boot_info *info) kernel_addr = load_kernel_info(info); } else { if(!qtest_enabled()) { - error_report("Need kernel filename\n"); - exit(1); + warn_report("No kernel provided, booting from flash drive."); } } diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 36d0cf6585..dcef44fe55 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -149,7 +149,7 @@ bool vfio_viommu_preset(VFIODevice *vbasedev) static void vfio_set_migration_error(int ret) { - if (migration_is_setup_or_active()) { + if (migration_is_running()) { migration_file_set_error(ret, NULL); } } diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index ae1e81d7ba..80ada89551 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -188,7 +188,7 @@ static bool virtio_mem_is_busy(void) * after plugging them) until we're running on the destination (as we didn't * migrate these blocks when they were unplugged). */ - return migration_in_incoming_postcopy() || !migration_is_idle(); + return migration_in_incoming_postcopy() || migration_is_running(); } typedef int (*virtio_mem_range_cb)(VirtIOMEM *vmem, void *arg, diff --git a/include/migration/misc.h b/include/migration/misc.h index bfadc5613b..804eb23c06 100644 --- a/include/migration/misc.h +++ b/include/migration/misc.h @@ -39,7 +39,6 @@ void precopy_add_notifier(NotifierWithReturn *n); void precopy_remove_notifier(NotifierWithReturn *n); int precopy_notify(PrecopyNotifyReason reason, Error **errp); -void ram_mig_init(void); void qemu_guest_free_page_hint(void *addr, size_t len); bool migrate_ram_is_ignored(RAMBlock *block); @@ -53,11 +52,11 @@ void dump_vmstate_json_to_file(FILE *out_fp); /* migration/migration.c */ void migration_object_init(void); void migration_shutdown(void); -bool migration_is_idle(void); + bool migration_is_active(void); bool migration_is_device(void); +bool migration_is_running(void); bool migration_thread_is_self(void); -bool migration_is_setup_or_active(void); typedef enum MigrationEventType { MIG_EVENT_PRECOPY_SETUP, @@ -96,7 +95,6 @@ void migration_add_notifier_mode(NotifierWithReturn *notify, MigrationNotifyFunc func, MigMode mode); void migration_remove_notifier(NotifierWithReturn *notify); -bool migration_is_running(void); void migration_file_set_error(int ret, Error *err); /* True if incoming migration entered POSTCOPY_INCOMING_DISCARD */ @@ -108,7 +106,4 @@ bool migration_incoming_postcopy_advised(void); /* True if background snapshot is active */ bool migration_in_bg_snapshot(void); -/* migration/block-dirty-bitmap.c */ -void dirty_bitmap_mig_init(void); - #endif diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index b72917073d..d4a2231306 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -702,6 +702,31 @@ extern "C" { #define I915_FORMAT_MOD_4_TILED_MTL_RC_CCS_CC fourcc_mod_code(INTEL, 15) /* + * Intel Color Control Surfaces (CCS) for graphics ver. 20 unified compression + * on integrated graphics + * + * The main surface is Tile 4 and at plane index 0. For semi-planar formats + * like NV12, the Y and UV planes are Tile 4 and are located at plane indices + * 0 and 1, respectively. The CCS for all planes are stored outside of the + * GEM object in a reserved memory area dedicated for the storage of the + * CCS data for all compressible GEM objects. + */ +#define I915_FORMAT_MOD_4_TILED_LNL_CCS fourcc_mod_code(INTEL, 16) + +/* + * Intel Color Control Surfaces (CCS) for graphics ver. 20 unified compression + * on discrete graphics + * + * The main surface is Tile 4 and at plane index 0. For semi-planar formats + * like NV12, the Y and UV planes are Tile 4 and are located at plane indices + * 0 and 1, respectively. The CCS for all planes are stored outside of the + * GEM object in a reserved memory area dedicated for the storage of the + * CCS data for all compressible GEM objects. The GEM object must be stored in + * contiguous memory with a size aligned to 64KB + */ +#define I915_FORMAT_MOD_4_TILED_BMG_CCS fourcc_mod_code(INTEL, 17) + +/* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * * Macroblocks are laid in a Z-shape, and each pixel data is following the @@ -1475,6 +1500,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) #define AMD_FMT_MOD_TILE_VER_GFX10 2 #define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3 #define AMD_FMT_MOD_TILE_VER_GFX11 4 +#define AMD_FMT_MOD_TILE_VER_GFX12 5 /* * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical @@ -1485,6 +1511,8 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) /* * 64K_D for non-32 bpp is the same for GFX9/GFX10/GFX10_RBPLUS and hence has * GFX9 as canonical version. + * + * 64K_D_2D on GFX12 is identical to 64K_D on GFX11. */ #define AMD_FMT_MOD_TILE_GFX9_64K_D 10 #define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25 @@ -1492,6 +1520,21 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) #define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27 #define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31 +/* Gfx12 swizzle modes: + * 0 - LINEAR + * 1 - 256B_2D - 2D block dimensions + * 2 - 4KB_2D + * 3 - 64KB_2D + * 4 - 256KB_2D + * 5 - 4KB_3D - 3D block dimensions + * 6 - 64KB_3D + * 7 - 256KB_3D + */ +#define AMD_FMT_MOD_TILE_GFX12_256B_2D 1 +#define AMD_FMT_MOD_TILE_GFX12_4K_2D 2 +#define AMD_FMT_MOD_TILE_GFX12_64K_2D 3 +#define AMD_FMT_MOD_TILE_GFX12_256K_2D 4 + #define AMD_FMT_MOD_DCC_BLOCK_64B 0 #define AMD_FMT_MOD_DCC_BLOCK_128B 1 #define AMD_FMT_MOD_DCC_BLOCK_256B 2 diff --git a/include/standard-headers/linux/const.h b/include/standard-headers/linux/const.h index 1eb84b5087..2122610de7 100644 --- a/include/standard-headers/linux/const.h +++ b/include/standard-headers/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing __asm__ support + * + * __BIT128() would not work in the __asm__ code, as it shifts an + * 'unsigned __init128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting __asm__ code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index b0b4b68410..b05e84825b 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -753,6 +753,197 @@ enum ethtool_module_power_mode { }; /** + * enum ethtool_c33_pse_ext_state - groups of PSE extended states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_STATE_ERROR_CONDITION: Group of error_condition states + * @ETHTOOL_C33_PSE_EXT_STATE_MR_MPS_VALID: Group of mr_mps_valid states + * @ETHTOOL_C33_PSE_EXT_STATE_MR_PSE_ENABLE: Group of mr_pse_enable states + * @ETHTOOL_C33_PSE_EXT_STATE_OPTION_DETECT_TED: Group of option_detect_ted + * states + * @ETHTOOL_C33_PSE_EXT_STATE_OPTION_VPORT_LIM: Group of option_vport_lim states + * @ETHTOOL_C33_PSE_EXT_STATE_OVLD_DETECTED: Group of ovld_detected states + * @ETHTOOL_C33_PSE_EXT_STATE_PD_DLL_POWER_TYPE: Group of pd_dll_power_type + * states + * @ETHTOOL_C33_PSE_EXT_STATE_POWER_NOT_AVAILABLE: Group of power_not_available + * states + * @ETHTOOL_C33_PSE_EXT_STATE_SHORT_DETECTED: Group of short_detected states + */ +enum ethtool_c33_pse_ext_state { + ETHTOOL_C33_PSE_EXT_STATE_ERROR_CONDITION = 1, + ETHTOOL_C33_PSE_EXT_STATE_MR_MPS_VALID, + ETHTOOL_C33_PSE_EXT_STATE_MR_PSE_ENABLE, + ETHTOOL_C33_PSE_EXT_STATE_OPTION_DETECT_TED, + ETHTOOL_C33_PSE_EXT_STATE_OPTION_VPORT_LIM, + ETHTOOL_C33_PSE_EXT_STATE_OVLD_DETECTED, + ETHTOOL_C33_PSE_EXT_STATE_PD_DLL_POWER_TYPE, + ETHTOOL_C33_PSE_EXT_STATE_POWER_NOT_AVAILABLE, + ETHTOOL_C33_PSE_EXT_STATE_SHORT_DETECTED, +}; + +/** + * enum ethtool_c33_pse_ext_substate_mr_mps_valid - mr_mps_valid states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_DETECTED_UNDERLOAD: Underload + * state + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_CONNECTION_OPEN: Port is not + * connected + * + * The PSE monitors either the DC or AC Maintain Power Signature + * (MPS, see 33.2.9.1). This variable indicates the presence or absence of + * a valid MPS. + */ +enum ethtool_c33_pse_ext_substate_mr_mps_valid { + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_DETECTED_UNDERLOAD = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_MPS_VALID_CONNECTION_OPEN, +}; + +/** + * enum ethtool_c33_pse_ext_substate_error_condition - error_condition states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_NON_EXISTING_PORT: Non-existing + * port number + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNDEFINED_PORT: Undefined port + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_INTERNAL_HW_FAULT: Internal + * hardware fault + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_COMM_ERROR_AFTER_FORCE_ON: + * Communication error after force on + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNKNOWN_PORT_STATUS: Unknown + * port status + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_TURN_OFF: Host + * crash turn off + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_FORCE_SHUTDOWN: + * Host crash force shutdown + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_CONFIG_CHANGE: Configuration + * change + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_DETECTED_OVER_TEMP: Over + * temperature detected + * + * error_condition is a variable indicating the status of + * implementation-specific fault conditions or optionally other system faults + * that prevent the PSE from meeting the specifications in Table 33–11 and that + * require the PSE not to source power. These error conditions are different + * from those monitored by the state diagrams in Figure 33–10. + */ +enum ethtool_c33_pse_ext_substate_error_condition { + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_NON_EXISTING_PORT = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNDEFINED_PORT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_INTERNAL_HW_FAULT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_COMM_ERROR_AFTER_FORCE_ON, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_UNKNOWN_PORT_STATUS, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_TURN_OFF, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_HOST_CRASH_FORCE_SHUTDOWN, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_CONFIG_CHANGE, + ETHTOOL_C33_PSE_EXT_SUBSTATE_ERROR_CONDITION_DETECTED_OVER_TEMP, +}; + +/** + * enum ethtool_c33_pse_ext_substate_mr_pse_enable - mr_pse_enable states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_PSE_ENABLE_DISABLE_PIN_ACTIVE: Disable + * pin active + * + * mr_pse_enable is control variable that selects PSE operation and test + * functions. + */ +enum ethtool_c33_pse_ext_substate_mr_pse_enable { + ETHTOOL_C33_PSE_EXT_SUBSTATE_MR_PSE_ENABLE_DISABLE_PIN_ACTIVE = 1, +}; + +/** + * enum ethtool_c33_pse_ext_substate_option_detect_ted - option_detect_ted + * states functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_DET_IN_PROCESS: Detection + * in process + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_CONNECTION_CHECK_ERROR: + * Connection check error + * + * option_detect_ted is a variable indicating if detection can be performed + * by the PSE during the ted_timer interval. + */ +enum ethtool_c33_pse_ext_substate_option_detect_ted { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_DET_IN_PROCESS = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_DETECT_TED_CONNECTION_CHECK_ERROR, +}; + +/** + * enum ethtool_c33_pse_ext_substate_option_vport_lim - option_vport_lim states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_HIGH_VOLTAGE: Main supply + * voltage is high + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_LOW_VOLTAGE: Main supply + * voltage is low + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_VOLTAGE_INJECTION: Voltage + * injection into the port + * + * option_vport_lim is an optional variable indicates if VPSE is out of the + * operating range during normal operating state. + */ +enum ethtool_c33_pse_ext_substate_option_vport_lim { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_HIGH_VOLTAGE = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_LOW_VOLTAGE, + ETHTOOL_C33_PSE_EXT_SUBSTATE_OPTION_VPORT_LIM_VOLTAGE_INJECTION, +}; + +/** + * enum ethtool_c33_pse_ext_substate_ovld_detected - ovld_detected states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_OVLD_DETECTED_OVERLOAD: Overload state + * + * ovld_detected is a variable indicating if the PSE output current has been + * in an overload condition (see 33.2.7.6) for at least TCUT of a one-second + * sliding time. + */ +enum ethtool_c33_pse_ext_substate_ovld_detected { + ETHTOOL_C33_PSE_EXT_SUBSTATE_OVLD_DETECTED_OVERLOAD = 1, +}; + +/** + * enum ethtool_c33_pse_ext_substate_power_not_available - power_not_available + * states functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_BUDGET_EXCEEDED: Power + * budget exceeded for the controller + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PORT_PW_LIMIT_EXCEEDS_CONTROLLER_BUDGET: + * Configured port power limit exceeded controller power budget + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PD_REQUEST_EXCEEDS_PORT_LIMIT: + * Power request from PD exceeds port limit + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_HW_PW_LIMIT: Power + * denied due to Hardware power limit + * + * power_not_available is a variable that is asserted in an + * implementation-dependent manner when the PSE is no longer capable of + * sourcing sufficient power to support the attached PD. Sufficient power + * is defined by classification; see 33.2.6. + */ +enum ethtool_c33_pse_ext_substate_power_not_available { + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_BUDGET_EXCEEDED = 1, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PORT_PW_LIMIT_EXCEEDS_CONTROLLER_BUDGET, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_PD_REQUEST_EXCEEDS_PORT_LIMIT, + ETHTOOL_C33_PSE_EXT_SUBSTATE_POWER_NOT_AVAILABLE_HW_PW_LIMIT, +}; + +/** + * enum ethtool_c33_pse_ext_substate_short_detected - short_detected states + * functions. IEEE 802.3-2022 33.2.4.4 Variables + * + * @ETHTOOL_C33_PSE_EXT_SUBSTATE_SHORT_DETECTED_SHORT_CONDITION: Short + * condition was detected + * + * short_detected is a variable indicating if the PSE output current has been + * in a short circuit condition for TLIM within a sliding window (see 33.2.7.7). + */ +enum ethtool_c33_pse_ext_substate_short_detected { + ETHTOOL_C33_PSE_EXT_SUBSTATE_SHORT_DETECTED_SHORT_CONDITION = 1, +}; + +/** * enum ethtool_pse_types - Types of PSE controller. * @ETHTOOL_PSE_UNKNOWN: Type of PSE controller is unknown * @ETHTOOL_PSE_PODL: PSE controller which support PoDL @@ -878,6 +1069,24 @@ enum ethtool_mm_verify_status { }; /** + * enum ethtool_module_fw_flash_status - plug-in module firmware flashing status + * @ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED: The firmware flashing process has + * started. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS: The firmware flashing process + * is in progress. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED: The firmware flashing process was + * completed successfully. + * @ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR: The firmware flashing process was + * stopped due to an error. + */ +enum ethtool_module_fw_flash_status { + ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED = 1, + ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS, + ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED, + ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR, +}; + +/** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS * @string_set: String set ID; one of &enum ethtool_stringset @@ -1845,6 +2054,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_10baseT1S_Full_BIT = 99, ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, + ETHTOOL_LINK_MODE_10baseT1BRR_Full_BIT = 102, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS @@ -2323,4 +2533,20 @@ struct ethtool_link_settings { * uint32_t map_lp_advertising[link_mode_masks_nwords]; */ }; + +/** + * enum phy_upstream - Represents the upstream component a given PHY device + * is connected to, as in what is on the other end of the MII bus. Most PHYs + * will be attached to an Ethernet MAC controller, but in some cases, there's + * an intermediate PHY used as a media-converter, which will driver another + * MII interface as its output. + * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, + * or ethernet controller) + * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) + */ +enum phy_upstream { + PHY_UPSTREAM_MAC, + PHY_UPSTREAM_PHY, +}; + #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h index bac9dbc49f..889e12ad15 100644 --- a/include/standard-headers/linux/fuse.h +++ b/include/standard-headers/linux/fuse.h @@ -217,6 +217,9 @@ * - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag * - add FUSE_NO_EXPORT_SUPPORT init flag * - add FUSE_NOTIFY_RESEND, add FUSE_HAS_RESEND init flag + * + * 7.41 + * - add FUSE_ALLOW_IDMAP */ #ifndef _LINUX_FUSE_H @@ -248,7 +251,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 40 +#define FUSE_KERNEL_MINOR_VERSION 41 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -417,6 +420,7 @@ struct fuse_file_lock { * FUSE_NO_EXPORT_SUPPORT: explicitly disable export support * FUSE_HAS_RESEND: kernel supports resending pending requests, and the high bit * of the request ID indicates resend requests + * FUSE_ALLOW_IDMAP: allow creation of idmapped mounts */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -462,6 +466,7 @@ struct fuse_file_lock { /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP +#define FUSE_ALLOW_IDMAP (1ULL << 40) /** * CUSE INIT request/reply flags @@ -980,6 +985,21 @@ struct fuse_fallocate_in { */ #define FUSE_UNIQUE_RESEND (1ULL << 63) +/** + * This value will be set by the kernel to + * (struct fuse_in_header).{uid,gid} fields in + * case when: + * - fuse daemon enabled FUSE_ALLOW_IDMAP + * - idmapping information is not available and uid/gid + * can not be mapped in accordance with an idmapping. + * + * Note: an idmapping information always available + * for inode creation operations like: + * FUSE_MKNOD, FUSE_SYMLINK, FUSE_MKDIR, FUSE_TMPFILE, + * FUSE_CREATE and FUSE_RENAME2 (with RENAME_WHITEOUT). + */ +#define FUSE_INVALID_UIDGID ((uint32_t)(-1)) + struct fuse_in_header { uint32_t len; uint32_t opcode; diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index 2221b0c383..50b2b7497e 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -618,6 +618,8 @@ #define KEY_CAMERA_ACCESS_ENABLE 0x24b /* Enables programmatic access to camera devices. (HUTRR72) */ #define KEY_CAMERA_ACCESS_DISABLE 0x24c /* Disables programmatic access to camera devices. (HUTRR72) */ #define KEY_CAMERA_ACCESS_TOGGLE 0x24d /* Toggles the current state of the camera access control. (HUTRR72) */ +#define KEY_ACCESSIBILITY 0x24e /* Toggles the system bound accessibility UI/command (HUTRR116) */ +#define KEY_DO_NOT_DISTURB 0x24f /* Toggles the system-wide "Do Not Disturb" control (HUTRR94)*/ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index 94c00996e6..12323b3334 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -634,9 +634,11 @@ #define PCI_EXP_RTCTL_SENFEE 0x0002 /* System Error on Non-Fatal Error */ #define PCI_EXP_RTCTL_SEFEE 0x0004 /* System Error on Fatal Error */ #define PCI_EXP_RTCTL_PMEIE 0x0008 /* PME Interrupt Enable */ -#define PCI_EXP_RTCTL_CRSSVE 0x0010 /* CRS Software Visibility Enable */ +#define PCI_EXP_RTCTL_RRS_SVE 0x0010 /* Config RRS Software Visibility Enable */ +#define PCI_EXP_RTCTL_CRSSVE PCI_EXP_RTCTL_RRS_SVE /* compatibility */ #define PCI_EXP_RTCAP 0x1e /* Root Capabilities */ -#define PCI_EXP_RTCAP_CRSVIS 0x0001 /* CRS Software Visibility capability */ +#define PCI_EXP_RTCAP_RRS_SV 0x0001 /* Config RRS Software Visibility */ +#define PCI_EXP_RTCAP_CRSVIS PCI_EXP_RTCAP_RRS_SV /* compatibility */ #define PCI_EXP_RTSTA 0x20 /* Root Status */ #define PCI_EXP_RTSTA_PME_RQ_ID 0x0000ffff /* PME Requester ID */ #define PCI_EXP_RTSTA_PME 0x00010000 /* PME status */ @@ -740,6 +742,7 @@ #define PCI_EXT_CAP_ID_DVSEC 0x23 /* Designated Vendor-Specific */ #define PCI_EXT_CAP_ID_DLF 0x25 /* Data Link Feature */ #define PCI_EXT_CAP_ID_PL_16GT 0x26 /* Physical Layer 16.0 GT/s */ +#define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ #define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE @@ -1121,6 +1124,40 @@ #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0 #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4 +/* Native PCIe Enclosure Management */ +#define PCI_NPEM_CAP 0x04 /* NPEM capability register */ +#define PCI_NPEM_CAP_CAPABLE 0x00000001 /* NPEM Capable */ + +#define PCI_NPEM_CTRL 0x08 /* NPEM control register */ +#define PCI_NPEM_CTRL_ENABLE 0x00000001 /* NPEM Enable */ + +/* + * Native PCIe Enclosure Management indication bits and Reset command bit + * are corresponding for capability and control registers. + */ +#define PCI_NPEM_CMD_RESET 0x00000002 /* Reset Command */ +#define PCI_NPEM_IND_OK 0x00000004 /* OK */ +#define PCI_NPEM_IND_LOCATE 0x00000008 /* Locate */ +#define PCI_NPEM_IND_FAIL 0x00000010 /* Fail */ +#define PCI_NPEM_IND_REBUILD 0x00000020 /* Rebuild */ +#define PCI_NPEM_IND_PFA 0x00000040 /* Predicted Failure Analysis */ +#define PCI_NPEM_IND_HOTSPARE 0x00000080 /* Hot Spare */ +#define PCI_NPEM_IND_ICA 0x00000100 /* In Critical Array */ +#define PCI_NPEM_IND_IFA 0x00000200 /* In Failed Array */ +#define PCI_NPEM_IND_IDT 0x00000400 /* Device Type */ +#define PCI_NPEM_IND_DISABLED 0x00000800 /* Disabled */ +#define PCI_NPEM_IND_SPEC_0 0x01000000 +#define PCI_NPEM_IND_SPEC_1 0x02000000 +#define PCI_NPEM_IND_SPEC_2 0x04000000 +#define PCI_NPEM_IND_SPEC_3 0x08000000 +#define PCI_NPEM_IND_SPEC_4 0x10000000 +#define PCI_NPEM_IND_SPEC_5 0x20000000 +#define PCI_NPEM_IND_SPEC_6 0x40000000 +#define PCI_NPEM_IND_SPEC_7 0x80000000 + +#define PCI_NPEM_STATUS 0x0c /* NPEM status register */ +#define PCI_NPEM_STATUS_CC 0x00000001 /* Command Completed */ + /* Data Object Exchange */ #define PCI_DOE_CAP 0x04 /* DOE Capabilities Register */ #define PCI_DOE_CAP_INT_SUP 0x00000001 /* Interrupt Support */ diff --git a/include/standard-headers/linux/virtio_balloon.h b/include/standard-headers/linux/virtio_balloon.h index f343bfefd8..3121cd2e0e 100644 --- a/include/standard-headers/linux/virtio_balloon.h +++ b/include/standard-headers/linux/virtio_balloon.h @@ -71,7 +71,13 @@ struct virtio_balloon_config { #define VIRTIO_BALLOON_S_CACHES 7 /* Disk caches */ #define VIRTIO_BALLOON_S_HTLB_PGALLOC 8 /* Hugetlb page allocations */ #define VIRTIO_BALLOON_S_HTLB_PGFAIL 9 /* Hugetlb page allocation failures */ -#define VIRTIO_BALLOON_S_NR 10 +#define VIRTIO_BALLOON_S_OOM_KILL 10 /* OOM killer invocations */ +#define VIRTIO_BALLOON_S_ALLOC_STALL 11 /* Stall count of memory allocatoin */ +#define VIRTIO_BALLOON_S_ASYNC_SCAN 12 /* Amount of memory scanned asynchronously */ +#define VIRTIO_BALLOON_S_DIRECT_SCAN 13 /* Amount of memory scanned directly */ +#define VIRTIO_BALLOON_S_ASYNC_RECLAIM 14 /* Amount of memory reclaimed asynchronously */ +#define VIRTIO_BALLOON_S_DIRECT_RECLAIM 15 /* Amount of memory reclaimed directly */ +#define VIRTIO_BALLOON_S_NR 16 #define VIRTIO_BALLOON_S_NAMES_WITH_PREFIX(VIRTIO_BALLOON_S_NAMES_prefix) { \ VIRTIO_BALLOON_S_NAMES_prefix "swap-in", \ @@ -83,7 +89,13 @@ struct virtio_balloon_config { VIRTIO_BALLOON_S_NAMES_prefix "available-memory", \ VIRTIO_BALLOON_S_NAMES_prefix "disk-caches", \ VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-allocations", \ - VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures" \ + VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures", \ + VIRTIO_BALLOON_S_NAMES_prefix "oom-kills", \ + VIRTIO_BALLOON_S_NAMES_prefix "alloc-stalls", \ + VIRTIO_BALLOON_S_NAMES_prefix "async-scans", \ + VIRTIO_BALLOON_S_NAMES_prefix "direct-scans", \ + VIRTIO_BALLOON_S_NAMES_prefix "async-reclaims", \ + VIRTIO_BALLOON_S_NAMES_prefix "direct-reclaims" \ } #define VIRTIO_BALLOON_S_NAMES VIRTIO_BALLOON_S_NAMES_WITH_PREFIX("") diff --git a/include/standard-headers/linux/virtio_gpu.h b/include/standard-headers/linux/virtio_gpu.h index 2db643ed8f..6459fdb9fb 100644 --- a/include/standard-headers/linux/virtio_gpu.h +++ b/include/standard-headers/linux/virtio_gpu.h @@ -311,6 +311,7 @@ struct virtio_gpu_cmd_submit { #define VIRTIO_GPU_CAPSET_VIRGL2 2 /* 3 is reserved for gfxstream */ #define VIRTIO_GPU_CAPSET_VENUS 4 +#define VIRTIO_GPU_CAPSET_DRM 6 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ struct virtio_gpu_get_capset_info { diff --git a/include/sysemu/cpu-throttle.h b/include/sysemu/cpu-throttle.h index d65bdef6d0..420702b8d3 100644 --- a/include/sysemu/cpu-throttle.h +++ b/include/sysemu/cpu-throttle.h @@ -65,4 +65,18 @@ bool cpu_throttle_active(void); */ int cpu_throttle_get_percentage(void); +/** + * cpu_throttle_dirty_sync_timer_tick: + * + * Dirty sync timer hook. + */ +void cpu_throttle_dirty_sync_timer_tick(void *opaque); + +/** + * cpu_throttle_dirty_sync_timer: + * + * Start or stop the dirty sync timer. + */ +void cpu_throttle_dirty_sync_timer(bool enable); + #endif /* SYSEMU_CPU_THROTTLE_H */ diff --git a/linux-headers/asm-arm64/mman.h b/linux-headers/asm-arm64/mman.h index d0dbfe9587..7b500a3a7b 100644 --- a/linux-headers/asm-arm64/mman.h +++ b/linux-headers/asm-arm64/mman.h @@ -7,4 +7,13 @@ #define PROT_BTI 0x10 /* BTI guarded page */ #define PROT_MTE 0x20 /* Normal Tagged mapping */ +/* Override any generic PKEY permission defines */ +#define PKEY_DISABLE_EXECUTE 0x4 +#define PKEY_DISABLE_READ 0x8 +#undef PKEY_ACCESS_MASK +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE |\ + PKEY_DISABLE_READ |\ + PKEY_DISABLE_EXECUTE) + #endif /* ! _UAPI__ASM_MMAN_H */ diff --git a/linux-headers/asm-arm64/unistd.h b/linux-headers/asm-arm64/unistd.h index ce2ee8f1e3..df36f23876 100644 --- a/linux-headers/asm-arm64/unistd.h +++ b/linux-headers/asm-arm64/unistd.h @@ -1,25 +1,2 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (C) 2012 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#define __ARCH_WANT_RENAMEAT -#define __ARCH_WANT_NEW_STAT -#define __ARCH_WANT_SET_GET_RLIMIT -#define __ARCH_WANT_TIME32_SYSCALLS -#define __ARCH_WANT_SYS_CLONE3 -#define __ARCH_WANT_MEMFD_SECRET - -#include <asm-generic/unistd.h> +#include <asm/unistd_64.h> diff --git a/linux-headers/asm-arm64/unistd_64.h b/linux-headers/asm-arm64/unistd_64.h new file mode 100644 index 0000000000..99a1d70459 --- /dev/null +++ b/linux-headers/asm-arm64/unistd_64.h @@ -0,0 +1,324 @@ +#ifndef _ASM_UNISTD_64_H +#define _ASM_UNISTD_64_H + +#define __NR_io_setup 0 +#define __NR_io_destroy 1 +#define __NR_io_submit 2 +#define __NR_io_cancel 3 +#define __NR_io_getevents 4 +#define __NR_setxattr 5 +#define __NR_lsetxattr 6 +#define __NR_fsetxattr 7 +#define __NR_getxattr 8 +#define __NR_lgetxattr 9 +#define __NR_fgetxattr 10 +#define __NR_listxattr 11 +#define __NR_llistxattr 12 +#define __NR_flistxattr 13 +#define __NR_removexattr 14 +#define __NR_lremovexattr 15 +#define __NR_fremovexattr 16 +#define __NR_getcwd 17 +#define __NR_lookup_dcookie 18 +#define __NR_eventfd2 19 +#define __NR_epoll_create1 20 +#define __NR_epoll_ctl 21 +#define __NR_epoll_pwait 22 +#define __NR_dup 23 +#define __NR_dup3 24 +#define __NR_fcntl 25 +#define __NR_inotify_init1 26 +#define __NR_inotify_add_watch 27 +#define __NR_inotify_rm_watch 28 +#define __NR_ioctl 29 +#define __NR_ioprio_set 30 +#define __NR_ioprio_get 31 +#define __NR_flock 32 +#define __NR_mknodat 33 +#define __NR_mkdirat 34 +#define __NR_unlinkat 35 +#define __NR_symlinkat 36 +#define __NR_linkat 37 +#define __NR_renameat 38 +#define __NR_umount2 39 +#define __NR_mount 40 +#define __NR_pivot_root 41 +#define __NR_nfsservctl 42 +#define __NR_statfs 43 +#define __NR_fstatfs 44 +#define __NR_truncate 45 +#define __NR_ftruncate 46 +#define __NR_fallocate 47 +#define __NR_faccessat 48 +#define __NR_chdir 49 +#define __NR_fchdir 50 +#define __NR_chroot 51 +#define __NR_fchmod 52 +#define __NR_fchmodat 53 +#define __NR_fchownat 54 +#define __NR_fchown 55 +#define __NR_openat 56 +#define __NR_close 57 +#define __NR_vhangup 58 +#define __NR_pipe2 59 +#define __NR_quotactl 60 +#define __NR_getdents64 61 +#define __NR_lseek 62 +#define __NR_read 63 +#define __NR_write 64 +#define __NR_readv 65 +#define __NR_writev 66 +#define __NR_pread64 67 +#define __NR_pwrite64 68 +#define __NR_preadv 69 +#define __NR_pwritev 70 +#define __NR_sendfile 71 +#define __NR_pselect6 72 +#define __NR_ppoll 73 +#define __NR_signalfd4 74 +#define __NR_vmsplice 75 +#define __NR_splice 76 +#define __NR_tee 77 +#define __NR_readlinkat 78 +#define __NR_newfstatat 79 +#define __NR_fstat 80 +#define __NR_sync 81 +#define __NR_fsync 82 +#define __NR_fdatasync 83 +#define __NR_sync_file_range 84 +#define __NR_timerfd_create 85 +#define __NR_timerfd_settime 86 +#define __NR_timerfd_gettime 87 +#define __NR_utimensat 88 +#define __NR_acct 89 +#define __NR_capget 90 +#define __NR_capset 91 +#define __NR_personality 92 +#define __NR_exit 93 +#define __NR_exit_group 94 +#define __NR_waitid 95 +#define __NR_set_tid_address 96 +#define __NR_unshare 97 +#define __NR_futex 98 +#define __NR_set_robust_list 99 +#define __NR_get_robust_list 100 +#define __NR_nanosleep 101 +#define __NR_getitimer 102 +#define __NR_setitimer 103 +#define __NR_kexec_load 104 +#define __NR_init_module 105 +#define __NR_delete_module 106 +#define __NR_timer_create 107 +#define __NR_timer_gettime 108 +#define __NR_timer_getoverrun 109 +#define __NR_timer_settime 110 +#define __NR_timer_delete 111 +#define __NR_clock_settime 112 +#define __NR_clock_gettime 113 +#define __NR_clock_getres 114 +#define __NR_clock_nanosleep 115 +#define __NR_syslog 116 +#define __NR_ptrace 117 +#define __NR_sched_setparam 118 +#define __NR_sched_setscheduler 119 +#define __NR_sched_getscheduler 120 +#define __NR_sched_getparam 121 +#define __NR_sched_setaffinity 122 +#define __NR_sched_getaffinity 123 +#define __NR_sched_yield 124 +#define __NR_sched_get_priority_max 125 +#define __NR_sched_get_priority_min 126 +#define __NR_sched_rr_get_interval 127 +#define __NR_restart_syscall 128 +#define __NR_kill 129 +#define __NR_tkill 130 +#define __NR_tgkill 131 +#define __NR_sigaltstack 132 +#define __NR_rt_sigsuspend 133 +#define __NR_rt_sigaction 134 +#define __NR_rt_sigprocmask 135 +#define __NR_rt_sigpending 136 +#define __NR_rt_sigtimedwait 137 +#define __NR_rt_sigqueueinfo 138 +#define __NR_rt_sigreturn 139 +#define __NR_setpriority 140 +#define __NR_getpriority 141 +#define __NR_reboot 142 +#define __NR_setregid 143 +#define __NR_setgid 144 +#define __NR_setreuid 145 +#define __NR_setuid 146 +#define __NR_setresuid 147 +#define __NR_getresuid 148 +#define __NR_setresgid 149 +#define __NR_getresgid 150 +#define __NR_setfsuid 151 +#define __NR_setfsgid 152 +#define __NR_times 153 +#define __NR_setpgid 154 +#define __NR_getpgid 155 +#define __NR_getsid 156 +#define __NR_setsid 157 +#define __NR_getgroups 158 +#define __NR_setgroups 159 +#define __NR_uname 160 +#define __NR_sethostname 161 +#define __NR_setdomainname 162 +#define __NR_getrlimit 163 +#define __NR_setrlimit 164 +#define __NR_getrusage 165 +#define __NR_umask 166 +#define __NR_prctl 167 +#define __NR_getcpu 168 +#define __NR_gettimeofday 169 +#define __NR_settimeofday 170 +#define __NR_adjtimex 171 +#define __NR_getpid 172 +#define __NR_getppid 173 +#define __NR_getuid 174 +#define __NR_geteuid 175 +#define __NR_getgid 176 +#define __NR_getegid 177 +#define __NR_gettid 178 +#define __NR_sysinfo 179 +#define __NR_mq_open 180 +#define __NR_mq_unlink 181 +#define __NR_mq_timedsend 182 +#define __NR_mq_timedreceive 183 +#define __NR_mq_notify 184 +#define __NR_mq_getsetattr 185 +#define __NR_msgget 186 +#define __NR_msgctl 187 +#define __NR_msgrcv 188 +#define __NR_msgsnd 189 +#define __NR_semget 190 +#define __NR_semctl 191 +#define __NR_semtimedop 192 +#define __NR_semop 193 +#define __NR_shmget 194 +#define __NR_shmctl 195 +#define __NR_shmat 196 +#define __NR_shmdt 197 +#define __NR_socket 198 +#define __NR_socketpair 199 +#define __NR_bind 200 +#define __NR_listen 201 +#define __NR_accept 202 +#define __NR_connect 203 +#define __NR_getsockname 204 +#define __NR_getpeername 205 +#define __NR_sendto 206 +#define __NR_recvfrom 207 +#define __NR_setsockopt 208 +#define __NR_getsockopt 209 +#define __NR_shutdown 210 +#define __NR_sendmsg 211 +#define __NR_recvmsg 212 +#define __NR_readahead 213 +#define __NR_brk 214 +#define __NR_munmap 215 +#define __NR_mremap 216 +#define __NR_add_key 217 +#define __NR_request_key 218 +#define __NR_keyctl 219 +#define __NR_clone 220 +#define __NR_execve 221 +#define __NR_mmap 222 +#define __NR_fadvise64 223 +#define __NR_swapon 224 +#define __NR_swapoff 225 +#define __NR_mprotect 226 +#define __NR_msync 227 +#define __NR_mlock 228 +#define __NR_munlock 229 +#define __NR_mlockall 230 +#define __NR_munlockall 231 +#define __NR_mincore 232 +#define __NR_madvise 233 +#define __NR_remap_file_pages 234 +#define __NR_mbind 235 +#define __NR_get_mempolicy 236 +#define __NR_set_mempolicy 237 +#define __NR_migrate_pages 238 +#define __NR_move_pages 239 +#define __NR_rt_tgsigqueueinfo 240 +#define __NR_perf_event_open 241 +#define __NR_accept4 242 +#define __NR_recvmmsg 243 +#define __NR_wait4 260 +#define __NR_prlimit64 261 +#define __NR_fanotify_init 262 +#define __NR_fanotify_mark 263 +#define __NR_name_to_handle_at 264 +#define __NR_open_by_handle_at 265 +#define __NR_clock_adjtime 266 +#define __NR_syncfs 267 +#define __NR_setns 268 +#define __NR_sendmmsg 269 +#define __NR_process_vm_readv 270 +#define __NR_process_vm_writev 271 +#define __NR_kcmp 272 +#define __NR_finit_module 273 +#define __NR_sched_setattr 274 +#define __NR_sched_getattr 275 +#define __NR_renameat2 276 +#define __NR_seccomp 277 +#define __NR_getrandom 278 +#define __NR_memfd_create 279 +#define __NR_bpf 280 +#define __NR_execveat 281 +#define __NR_userfaultfd 282 +#define __NR_membarrier 283 +#define __NR_mlock2 284 +#define __NR_copy_file_range 285 +#define __NR_preadv2 286 +#define __NR_pwritev2 287 +#define __NR_pkey_mprotect 288 +#define __NR_pkey_alloc 289 +#define __NR_pkey_free 290 +#define __NR_statx 291 +#define __NR_io_pgetevents 292 +#define __NR_rseq 293 +#define __NR_kexec_file_load 294 +#define __NR_pidfd_send_signal 424 +#define __NR_io_uring_setup 425 +#define __NR_io_uring_enter 426 +#define __NR_io_uring_register 427 +#define __NR_open_tree 428 +#define __NR_move_mount 429 +#define __NR_fsopen 430 +#define __NR_fsconfig 431 +#define __NR_fsmount 432 +#define __NR_fspick 433 +#define __NR_pidfd_open 434 +#define __NR_clone3 435 +#define __NR_close_range 436 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 +#define __NR_faccessat2 439 +#define __NR_process_madvise 440 +#define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 +#define __NR_memfd_secret 447 +#define __NR_process_mrelease 448 +#define __NR_futex_waitv 449 +#define __NR_set_mempolicy_home_node 450 +#define __NR_cachestat 451 +#define __NR_fchmodat2 452 +#define __NR_map_shadow_stack 453 +#define __NR_futex_wake 454 +#define __NR_futex_wait 455 +#define __NR_futex_requeue 456 +#define __NR_statmount 457 +#define __NR_listmount 458 +#define __NR_lsm_get_self_attr 459 +#define __NR_lsm_set_self_attr 460 +#define __NR_lsm_list_modules 461 +#define __NR_mseal 462 + + +#endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h index d983c48a3b..5bf6148cac 100644 --- a/linux-headers/asm-generic/unistd.h +++ b/linux-headers/asm-generic/unistd.h @@ -737,7 +737,7 @@ __SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SC_COMP(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 @@ -776,12 +776,8 @@ __SYSCALL(__NR_fsmount, sys_fsmount) __SYSCALL(__NR_fspick, sys_fspick) #define __NR_pidfd_open 434 __SYSCALL(__NR_pidfd_open, sys_pidfd_open) - -#ifdef __ARCH_WANT_SYS_CLONE3 #define __NR_clone3 435 __SYSCALL(__NR_clone3, sys_clone3) -#endif - #define __NR_close_range 436 __SYSCALL(__NR_close_range, sys_close_range) #define __NR_openat2 437 diff --git a/linux-headers/asm-loongarch/kvm.h b/linux-headers/asm-loongarch/kvm.h index f9abef3823..70d89070bf 100644 --- a/linux-headers/asm-loongarch/kvm.h +++ b/linux-headers/asm-loongarch/kvm.h @@ -64,6 +64,7 @@ struct kvm_fpu { #define KVM_REG_LOONGARCH_KVM (KVM_REG_LOONGARCH | 0x20000ULL) #define KVM_REG_LOONGARCH_FPSIMD (KVM_REG_LOONGARCH | 0x30000ULL) #define KVM_REG_LOONGARCH_CPUCFG (KVM_REG_LOONGARCH | 0x40000ULL) +#define KVM_REG_LOONGARCH_LBT (KVM_REG_LOONGARCH | 0x50000ULL) #define KVM_REG_LOONGARCH_MASK (KVM_REG_LOONGARCH | 0x70000ULL) #define KVM_CSR_IDX_MASK 0x7fff #define KVM_CPUCFG_IDX_MASK 0x7fff @@ -77,11 +78,34 @@ struct kvm_fpu { /* Debugging: Special instruction for software breakpoint */ #define KVM_REG_LOONGARCH_DEBUG_INST (KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 3) +/* LBT registers */ +#define KVM_REG_LOONGARCH_LBT_SCR0 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 1) +#define KVM_REG_LOONGARCH_LBT_SCR1 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 2) +#define KVM_REG_LOONGARCH_LBT_SCR2 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 3) +#define KVM_REG_LOONGARCH_LBT_SCR3 (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 4) +#define KVM_REG_LOONGARCH_LBT_EFLAGS (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 5) +#define KVM_REG_LOONGARCH_LBT_FTOP (KVM_REG_LOONGARCH_LBT | KVM_REG_SIZE_U64 | 6) + #define LOONGARCH_REG_SHIFT 3 #define LOONGARCH_REG_64(TYPE, REG) (TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT)) #define KVM_IOC_CSRID(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG) #define KVM_IOC_CPUCFG(REG) LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG) + +/* Device Control API on vm fd */ +#define KVM_LOONGARCH_VM_FEAT_CTRL 0 +#define KVM_LOONGARCH_VM_FEAT_LSX 0 +#define KVM_LOONGARCH_VM_FEAT_LASX 1 +#define KVM_LOONGARCH_VM_FEAT_X86BT 2 +#define KVM_LOONGARCH_VM_FEAT_ARMBT 3 +#define KVM_LOONGARCH_VM_FEAT_MIPSBT 4 +#define KVM_LOONGARCH_VM_FEAT_PMU 5 +#define KVM_LOONGARCH_VM_FEAT_PV_IPI 6 +#define KVM_LOONGARCH_VM_FEAT_PV_STEALTIME 7 + +/* Device Control API on vcpu fd */ #define KVM_LOONGARCH_VCPU_CPUCFG 0 +#define KVM_LOONGARCH_VCPU_PVTIME_CTRL 1 +#define KVM_LOONGARCH_VCPU_PVTIME_GPA 0 struct kvm_debug_exit_arch { }; diff --git a/linux-headers/asm-loongarch/kvm_para.h b/linux-headers/asm-loongarch/kvm_para.h new file mode 100644 index 0000000000..4ba4ad8db1 --- /dev/null +++ b/linux-headers/asm-loongarch/kvm_para.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_KVM_PARA_H +#define _ASM_KVM_PARA_H + +#include <linux/types.h> + +/* + * CPUCFG index area: 0x40000000 -- 0x400000ff + * SW emulation for KVM hypervirsor + */ +#define CPUCFG_KVM_BASE 0x40000000 +#define CPUCFG_KVM_SIZE 0x100 +#define CPUCFG_KVM_SIG (CPUCFG_KVM_BASE + 0) +#define KVM_SIGNATURE "KVM\0" +#define CPUCFG_KVM_FEATURE (CPUCFG_KVM_BASE + 4) +#define KVM_FEATURE_IPI 1 +#define KVM_FEATURE_STEAL_TIME 2 +/* BIT 24 - 31 are features configurable by user space vmm */ +#define KVM_FEATURE_VIRT_EXTIOI 24 + +#endif /* _ASM_KVM_PARA_H */ diff --git a/linux-headers/asm-loongarch/unistd.h b/linux-headers/asm-loongarch/unistd.h index fcb668984f..1f01980f9c 100644 --- a/linux-headers/asm-loongarch/unistd.h +++ b/linux-headers/asm-loongarch/unistd.h @@ -1,5 +1,3 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#define __ARCH_WANT_SYS_CLONE -#define __ARCH_WANT_SYS_CLONE3 -#include <asm-generic/unistd.h> +#include <asm/unistd_64.h> diff --git a/linux-headers/asm-loongarch/unistd_64.h b/linux-headers/asm-loongarch/unistd_64.h new file mode 100644 index 0000000000..887ea50cca --- /dev/null +++ b/linux-headers/asm-loongarch/unistd_64.h @@ -0,0 +1,320 @@ +#ifndef _ASM_UNISTD_64_H +#define _ASM_UNISTD_64_H + +#define __NR_io_setup 0 +#define __NR_io_destroy 1 +#define __NR_io_submit 2 +#define __NR_io_cancel 3 +#define __NR_io_getevents 4 +#define __NR_setxattr 5 +#define __NR_lsetxattr 6 +#define __NR_fsetxattr 7 +#define __NR_getxattr 8 +#define __NR_lgetxattr 9 +#define __NR_fgetxattr 10 +#define __NR_listxattr 11 +#define __NR_llistxattr 12 +#define __NR_flistxattr 13 +#define __NR_removexattr 14 +#define __NR_lremovexattr 15 +#define __NR_fremovexattr 16 +#define __NR_getcwd 17 +#define __NR_lookup_dcookie 18 +#define __NR_eventfd2 19 +#define __NR_epoll_create1 20 +#define __NR_epoll_ctl 21 +#define __NR_epoll_pwait 22 +#define __NR_dup 23 +#define __NR_dup3 24 +#define __NR_fcntl 25 +#define __NR_inotify_init1 26 +#define __NR_inotify_add_watch 27 +#define __NR_inotify_rm_watch 28 +#define __NR_ioctl 29 +#define __NR_ioprio_set 30 +#define __NR_ioprio_get 31 +#define __NR_flock 32 +#define __NR_mknodat 33 +#define __NR_mkdirat 34 +#define __NR_unlinkat 35 +#define __NR_symlinkat 36 +#define __NR_linkat 37 +#define __NR_umount2 39 +#define __NR_mount 40 +#define __NR_pivot_root 41 +#define __NR_nfsservctl 42 +#define __NR_statfs 43 +#define __NR_fstatfs 44 +#define __NR_truncate 45 +#define __NR_ftruncate 46 +#define __NR_fallocate 47 +#define __NR_faccessat 48 +#define __NR_chdir 49 +#define __NR_fchdir 50 +#define __NR_chroot 51 +#define __NR_fchmod 52 +#define __NR_fchmodat 53 +#define __NR_fchownat 54 +#define __NR_fchown 55 +#define __NR_openat 56 +#define __NR_close 57 +#define __NR_vhangup 58 +#define __NR_pipe2 59 +#define __NR_quotactl 60 +#define __NR_getdents64 61 +#define __NR_lseek 62 +#define __NR_read 63 +#define __NR_write 64 +#define __NR_readv 65 +#define __NR_writev 66 +#define __NR_pread64 67 +#define __NR_pwrite64 68 +#define __NR_preadv 69 +#define __NR_pwritev 70 +#define __NR_sendfile 71 +#define __NR_pselect6 72 +#define __NR_ppoll 73 +#define __NR_signalfd4 74 +#define __NR_vmsplice 75 +#define __NR_splice 76 +#define __NR_tee 77 +#define __NR_readlinkat 78 +#define __NR_newfstatat 79 +#define __NR_fstat 80 +#define __NR_sync 81 +#define __NR_fsync 82 +#define __NR_fdatasync 83 +#define __NR_sync_file_range 84 +#define __NR_timerfd_create 85 +#define __NR_timerfd_settime 86 +#define __NR_timerfd_gettime 87 +#define __NR_utimensat 88 +#define __NR_acct 89 +#define __NR_capget 90 +#define __NR_capset 91 +#define __NR_personality 92 +#define __NR_exit 93 +#define __NR_exit_group 94 +#define __NR_waitid 95 +#define __NR_set_tid_address 96 +#define __NR_unshare 97 +#define __NR_futex 98 +#define __NR_set_robust_list 99 +#define __NR_get_robust_list 100 +#define __NR_nanosleep 101 +#define __NR_getitimer 102 +#define __NR_setitimer 103 +#define __NR_kexec_load 104 +#define __NR_init_module 105 +#define __NR_delete_module 106 +#define __NR_timer_create 107 +#define __NR_timer_gettime 108 +#define __NR_timer_getoverrun 109 +#define __NR_timer_settime 110 +#define __NR_timer_delete 111 +#define __NR_clock_settime 112 +#define __NR_clock_gettime 113 +#define __NR_clock_getres 114 +#define __NR_clock_nanosleep 115 +#define __NR_syslog 116 +#define __NR_ptrace 117 +#define __NR_sched_setparam 118 +#define __NR_sched_setscheduler 119 +#define __NR_sched_getscheduler 120 +#define __NR_sched_getparam 121 +#define __NR_sched_setaffinity 122 +#define __NR_sched_getaffinity 123 +#define __NR_sched_yield 124 +#define __NR_sched_get_priority_max 125 +#define __NR_sched_get_priority_min 126 +#define __NR_sched_rr_get_interval 127 +#define __NR_restart_syscall 128 +#define __NR_kill 129 +#define __NR_tkill 130 +#define __NR_tgkill 131 +#define __NR_sigaltstack 132 +#define __NR_rt_sigsuspend 133 +#define __NR_rt_sigaction 134 +#define __NR_rt_sigprocmask 135 +#define __NR_rt_sigpending 136 +#define __NR_rt_sigtimedwait 137 +#define __NR_rt_sigqueueinfo 138 +#define __NR_rt_sigreturn 139 +#define __NR_setpriority 140 +#define __NR_getpriority 141 +#define __NR_reboot 142 +#define __NR_setregid 143 +#define __NR_setgid 144 +#define __NR_setreuid 145 +#define __NR_setuid 146 +#define __NR_setresuid 147 +#define __NR_getresuid 148 +#define __NR_setresgid 149 +#define __NR_getresgid 150 +#define __NR_setfsuid 151 +#define __NR_setfsgid 152 +#define __NR_times 153 +#define __NR_setpgid 154 +#define __NR_getpgid 155 +#define __NR_getsid 156 +#define __NR_setsid 157 +#define __NR_getgroups 158 +#define __NR_setgroups 159 +#define __NR_uname 160 +#define __NR_sethostname 161 +#define __NR_setdomainname 162 +#define __NR_getrusage 165 +#define __NR_umask 166 +#define __NR_prctl 167 +#define __NR_getcpu 168 +#define __NR_gettimeofday 169 +#define __NR_settimeofday 170 +#define __NR_adjtimex 171 +#define __NR_getpid 172 +#define __NR_getppid 173 +#define __NR_getuid 174 +#define __NR_geteuid 175 +#define __NR_getgid 176 +#define __NR_getegid 177 +#define __NR_gettid 178 +#define __NR_sysinfo 179 +#define __NR_mq_open 180 +#define __NR_mq_unlink 181 +#define __NR_mq_timedsend 182 +#define __NR_mq_timedreceive 183 +#define __NR_mq_notify 184 +#define __NR_mq_getsetattr 185 +#define __NR_msgget 186 +#define __NR_msgctl 187 +#define __NR_msgrcv 188 +#define __NR_msgsnd 189 +#define __NR_semget 190 +#define __NR_semctl 191 +#define __NR_semtimedop 192 +#define __NR_semop 193 +#define __NR_shmget 194 +#define __NR_shmctl 195 +#define __NR_shmat 196 +#define __NR_shmdt 197 +#define __NR_socket 198 +#define __NR_socketpair 199 +#define __NR_bind 200 +#define __NR_listen 201 +#define __NR_accept 202 +#define __NR_connect 203 +#define __NR_getsockname 204 +#define __NR_getpeername 205 +#define __NR_sendto 206 +#define __NR_recvfrom 207 +#define __NR_setsockopt 208 +#define __NR_getsockopt 209 +#define __NR_shutdown 210 +#define __NR_sendmsg 211 +#define __NR_recvmsg 212 +#define __NR_readahead 213 +#define __NR_brk 214 +#define __NR_munmap 215 +#define __NR_mremap 216 +#define __NR_add_key 217 +#define __NR_request_key 218 +#define __NR_keyctl 219 +#define __NR_clone 220 +#define __NR_execve 221 +#define __NR_mmap 222 +#define __NR_fadvise64 223 +#define __NR_swapon 224 +#define __NR_swapoff 225 +#define __NR_mprotect 226 +#define __NR_msync 227 +#define __NR_mlock 228 +#define __NR_munlock 229 +#define __NR_mlockall 230 +#define __NR_munlockall 231 +#define __NR_mincore 232 +#define __NR_madvise 233 +#define __NR_remap_file_pages 234 +#define __NR_mbind 235 +#define __NR_get_mempolicy 236 +#define __NR_set_mempolicy 237 +#define __NR_migrate_pages 238 +#define __NR_move_pages 239 +#define __NR_rt_tgsigqueueinfo 240 +#define __NR_perf_event_open 241 +#define __NR_accept4 242 +#define __NR_recvmmsg 243 +#define __NR_wait4 260 +#define __NR_prlimit64 261 +#define __NR_fanotify_init 262 +#define __NR_fanotify_mark 263 +#define __NR_name_to_handle_at 264 +#define __NR_open_by_handle_at 265 +#define __NR_clock_adjtime 266 +#define __NR_syncfs 267 +#define __NR_setns 268 +#define __NR_sendmmsg 269 +#define __NR_process_vm_readv 270 +#define __NR_process_vm_writev 271 +#define __NR_kcmp 272 +#define __NR_finit_module 273 +#define __NR_sched_setattr 274 +#define __NR_sched_getattr 275 +#define __NR_renameat2 276 +#define __NR_seccomp 277 +#define __NR_getrandom 278 +#define __NR_memfd_create 279 +#define __NR_bpf 280 +#define __NR_execveat 281 +#define __NR_userfaultfd 282 +#define __NR_membarrier 283 +#define __NR_mlock2 284 +#define __NR_copy_file_range 285 +#define __NR_preadv2 286 +#define __NR_pwritev2 287 +#define __NR_pkey_mprotect 288 +#define __NR_pkey_alloc 289 +#define __NR_pkey_free 290 +#define __NR_statx 291 +#define __NR_io_pgetevents 292 +#define __NR_rseq 293 +#define __NR_kexec_file_load 294 +#define __NR_pidfd_send_signal 424 +#define __NR_io_uring_setup 425 +#define __NR_io_uring_enter 426 +#define __NR_io_uring_register 427 +#define __NR_open_tree 428 +#define __NR_move_mount 429 +#define __NR_fsopen 430 +#define __NR_fsconfig 431 +#define __NR_fsmount 432 +#define __NR_fspick 433 +#define __NR_pidfd_open 434 +#define __NR_clone3 435 +#define __NR_close_range 436 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 +#define __NR_faccessat2 439 +#define __NR_process_madvise 440 +#define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 +#define __NR_process_mrelease 448 +#define __NR_futex_waitv 449 +#define __NR_set_mempolicy_home_node 450 +#define __NR_cachestat 451 +#define __NR_fchmodat2 452 +#define __NR_map_shadow_stack 453 +#define __NR_futex_wake 454 +#define __NR_futex_wait 455 +#define __NR_futex_requeue 456 +#define __NR_statmount 457 +#define __NR_listmount 458 +#define __NR_lsm_get_self_attr 459 +#define __NR_lsm_set_self_attr 460 +#define __NR_lsm_list_modules 461 +#define __NR_mseal 462 + + +#endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h index e878e7cc39..e97db32964 100644 --- a/linux-headers/asm-riscv/kvm.h +++ b/linux-headers/asm-riscv/kvm.h @@ -168,6 +168,13 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_ZTSO, KVM_RISCV_ISA_EXT_ZACAS, KVM_RISCV_ISA_EXT_SSCOFPMF, + KVM_RISCV_ISA_EXT_ZIMOP, + KVM_RISCV_ISA_EXT_ZCA, + KVM_RISCV_ISA_EXT_ZCB, + KVM_RISCV_ISA_EXT_ZCD, + KVM_RISCV_ISA_EXT_ZCF, + KVM_RISCV_ISA_EXT_ZCMOP, + KVM_RISCV_ISA_EXT_ZAWRS, KVM_RISCV_ISA_EXT_MAX, }; diff --git a/linux-headers/asm-riscv/unistd.h b/linux-headers/asm-riscv/unistd.h index 950ab3fd44..81896bbbf7 100644 --- a/linux-headers/asm-riscv/unistd.h +++ b/linux-headers/asm-riscv/unistd.h @@ -14,41 +14,10 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see <https://www.gnu.org/licenses/>. */ +#include <asm/bitsperlong.h> -#if defined(__LP64__) && !defined(__SYSCALL_COMPAT) -#define __ARCH_WANT_NEW_STAT -#define __ARCH_WANT_SET_GET_RLIMIT -#endif /* __LP64__ */ - -#define __ARCH_WANT_SYS_CLONE3 -#define __ARCH_WANT_MEMFD_SECRET - -#include <asm-generic/unistd.h> - -/* - * Allows the instruction cache to be flushed from userspace. Despite RISC-V - * having a direct 'fence.i' instruction available to userspace (which we - * can't trap!), that's not actually viable when running on Linux because the - * kernel might schedule a process on another hart. There is no way for - * userspace to handle this without invoking the kernel (as it doesn't know the - * thread->hart mappings), so we've defined a RISC-V specific system call to - * flush the instruction cache. - * - * __NR_riscv_flush_icache is defined to flush the instruction cache over an - * address range, with the flush applying to either all threads or just the - * caller. We don't currently do anything with the address range, that's just - * in there for forwards compatibility. - */ -#ifndef __NR_riscv_flush_icache -#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15) -#endif -__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache) - -/* - * Allows userspace to query the kernel for CPU architecture and - * microarchitecture details across a given set of CPUs. - */ -#ifndef __NR_riscv_hwprobe -#define __NR_riscv_hwprobe (__NR_arch_specific_syscall + 14) +#if __BITS_PER_LONG == 64 +#include <asm/unistd_64.h> +#else +#include <asm/unistd_32.h> #endif -__SYSCALL(__NR_riscv_hwprobe, sys_riscv_hwprobe) diff --git a/linux-headers/asm-riscv/unistd_32.h b/linux-headers/asm-riscv/unistd_32.h new file mode 100644 index 0000000000..9625743dfd --- /dev/null +++ b/linux-headers/asm-riscv/unistd_32.h @@ -0,0 +1,315 @@ +#ifndef _ASM_UNISTD_32_H +#define _ASM_UNISTD_32_H + +#define __NR_io_setup 0 +#define __NR_io_destroy 1 +#define __NR_io_submit 2 +#define __NR_io_cancel 3 +#define __NR_setxattr 5 +#define __NR_lsetxattr 6 +#define __NR_fsetxattr 7 +#define __NR_getxattr 8 +#define __NR_lgetxattr 9 +#define __NR_fgetxattr 10 +#define __NR_listxattr 11 +#define __NR_llistxattr 12 +#define __NR_flistxattr 13 +#define __NR_removexattr 14 +#define __NR_lremovexattr 15 +#define __NR_fremovexattr 16 +#define __NR_getcwd 17 +#define __NR_lookup_dcookie 18 +#define __NR_eventfd2 19 +#define __NR_epoll_create1 20 +#define __NR_epoll_ctl 21 +#define __NR_epoll_pwait 22 +#define __NR_dup 23 +#define __NR_dup3 24 +#define __NR_fcntl64 25 +#define __NR_inotify_init1 26 +#define __NR_inotify_add_watch 27 +#define __NR_inotify_rm_watch 28 +#define __NR_ioctl 29 +#define __NR_ioprio_set 30 +#define __NR_ioprio_get 31 +#define __NR_flock 32 +#define __NR_mknodat 33 +#define __NR_mkdirat 34 +#define __NR_unlinkat 35 +#define __NR_symlinkat 36 +#define __NR_linkat 37 +#define __NR_umount2 39 +#define __NR_mount 40 +#define __NR_pivot_root 41 +#define __NR_nfsservctl 42 +#define __NR_statfs64 43 +#define __NR_fstatfs64 44 +#define __NR_truncate64 45 +#define __NR_ftruncate64 46 +#define __NR_fallocate 47 +#define __NR_faccessat 48 +#define __NR_chdir 49 +#define __NR_fchdir 50 +#define __NR_chroot 51 +#define __NR_fchmod 52 +#define __NR_fchmodat 53 +#define __NR_fchownat 54 +#define __NR_fchown 55 +#define __NR_openat 56 +#define __NR_close 57 +#define __NR_vhangup 58 +#define __NR_pipe2 59 +#define __NR_quotactl 60 +#define __NR_getdents64 61 +#define __NR_llseek 62 +#define __NR_read 63 +#define __NR_write 64 +#define __NR_readv 65 +#define __NR_writev 66 +#define __NR_pread64 67 +#define __NR_pwrite64 68 +#define __NR_preadv 69 +#define __NR_pwritev 70 +#define __NR_sendfile64 71 +#define __NR_signalfd4 74 +#define __NR_vmsplice 75 +#define __NR_splice 76 +#define __NR_tee 77 +#define __NR_readlinkat 78 +#define __NR_sync 81 +#define __NR_fsync 82 +#define __NR_fdatasync 83 +#define __NR_sync_file_range 84 +#define __NR_timerfd_create 85 +#define __NR_acct 89 +#define __NR_capget 90 +#define __NR_capset 91 +#define __NR_personality 92 +#define __NR_exit 93 +#define __NR_exit_group 94 +#define __NR_waitid 95 +#define __NR_set_tid_address 96 +#define __NR_unshare 97 +#define __NR_set_robust_list 99 +#define __NR_get_robust_list 100 +#define __NR_getitimer 102 +#define __NR_setitimer 103 +#define __NR_kexec_load 104 +#define __NR_init_module 105 +#define __NR_delete_module 106 +#define __NR_timer_create 107 +#define __NR_timer_getoverrun 109 +#define __NR_timer_delete 111 +#define __NR_syslog 116 +#define __NR_ptrace 117 +#define __NR_sched_setparam 118 +#define __NR_sched_setscheduler 119 +#define __NR_sched_getscheduler 120 +#define __NR_sched_getparam 121 +#define __NR_sched_setaffinity 122 +#define __NR_sched_getaffinity 123 +#define __NR_sched_yield 124 +#define __NR_sched_get_priority_max 125 +#define __NR_sched_get_priority_min 126 +#define __NR_restart_syscall 128 +#define __NR_kill 129 +#define __NR_tkill 130 +#define __NR_tgkill 131 +#define __NR_sigaltstack 132 +#define __NR_rt_sigsuspend 133 +#define __NR_rt_sigaction 134 +#define __NR_rt_sigprocmask 135 +#define __NR_rt_sigpending 136 +#define __NR_rt_sigqueueinfo 138 +#define __NR_rt_sigreturn 139 +#define __NR_setpriority 140 +#define __NR_getpriority 141 +#define __NR_reboot 142 +#define __NR_setregid 143 +#define __NR_setgid 144 +#define __NR_setreuid 145 +#define __NR_setuid 146 +#define __NR_setresuid 147 +#define __NR_getresuid 148 +#define __NR_setresgid 149 +#define __NR_getresgid 150 +#define __NR_setfsuid 151 +#define __NR_setfsgid 152 +#define __NR_times 153 +#define __NR_setpgid 154 +#define __NR_getpgid 155 +#define __NR_getsid 156 +#define __NR_setsid 157 +#define __NR_getgroups 158 +#define __NR_setgroups 159 +#define __NR_uname 160 +#define __NR_sethostname 161 +#define __NR_setdomainname 162 +#define __NR_getrusage 165 +#define __NR_umask 166 +#define __NR_prctl 167 +#define __NR_getcpu 168 +#define __NR_getpid 172 +#define __NR_getppid 173 +#define __NR_getuid 174 +#define __NR_geteuid 175 +#define __NR_getgid 176 +#define __NR_getegid 177 +#define __NR_gettid 178 +#define __NR_sysinfo 179 +#define __NR_mq_open 180 +#define __NR_mq_unlink 181 +#define __NR_mq_notify 184 +#define __NR_mq_getsetattr 185 +#define __NR_msgget 186 +#define __NR_msgctl 187 +#define __NR_msgrcv 188 +#define __NR_msgsnd 189 +#define __NR_semget 190 +#define __NR_semctl 191 +#define __NR_semop 193 +#define __NR_shmget 194 +#define __NR_shmctl 195 +#define __NR_shmat 196 +#define __NR_shmdt 197 +#define __NR_socket 198 +#define __NR_socketpair 199 +#define __NR_bind 200 +#define __NR_listen 201 +#define __NR_accept 202 +#define __NR_connect 203 +#define __NR_getsockname 204 +#define __NR_getpeername 205 +#define __NR_sendto 206 +#define __NR_recvfrom 207 +#define __NR_setsockopt 208 +#define __NR_getsockopt 209 +#define __NR_shutdown 210 +#define __NR_sendmsg 211 +#define __NR_recvmsg 212 +#define __NR_readahead 213 +#define __NR_brk 214 +#define __NR_munmap 215 +#define __NR_mremap 216 +#define __NR_add_key 217 +#define __NR_request_key 218 +#define __NR_keyctl 219 +#define __NR_clone 220 +#define __NR_execve 221 +#define __NR_mmap2 222 +#define __NR_fadvise64_64 223 +#define __NR_swapon 224 +#define __NR_swapoff 225 +#define __NR_mprotect 226 +#define __NR_msync 227 +#define __NR_mlock 228 +#define __NR_munlock 229 +#define __NR_mlockall 230 +#define __NR_munlockall 231 +#define __NR_mincore 232 +#define __NR_madvise 233 +#define __NR_remap_file_pages 234 +#define __NR_mbind 235 +#define __NR_get_mempolicy 236 +#define __NR_set_mempolicy 237 +#define __NR_migrate_pages 238 +#define __NR_move_pages 239 +#define __NR_rt_tgsigqueueinfo 240 +#define __NR_perf_event_open 241 +#define __NR_accept4 242 +#define __NR_riscv_hwprobe 258 +#define __NR_riscv_flush_icache 259 +#define __NR_prlimit64 261 +#define __NR_fanotify_init 262 +#define __NR_fanotify_mark 263 +#define __NR_name_to_handle_at 264 +#define __NR_open_by_handle_at 265 +#define __NR_syncfs 267 +#define __NR_setns 268 +#define __NR_sendmmsg 269 +#define __NR_process_vm_readv 270 +#define __NR_process_vm_writev 271 +#define __NR_kcmp 272 +#define __NR_finit_module 273 +#define __NR_sched_setattr 274 +#define __NR_sched_getattr 275 +#define __NR_renameat2 276 +#define __NR_seccomp 277 +#define __NR_getrandom 278 +#define __NR_memfd_create 279 +#define __NR_bpf 280 +#define __NR_execveat 281 +#define __NR_userfaultfd 282 +#define __NR_membarrier 283 +#define __NR_mlock2 284 +#define __NR_copy_file_range 285 +#define __NR_preadv2 286 +#define __NR_pwritev2 287 +#define __NR_pkey_mprotect 288 +#define __NR_pkey_alloc 289 +#define __NR_pkey_free 290 +#define __NR_statx 291 +#define __NR_rseq 293 +#define __NR_kexec_file_load 294 +#define __NR_clock_gettime64 403 +#define __NR_clock_settime64 404 +#define __NR_clock_adjtime64 405 +#define __NR_clock_getres_time64 406 +#define __NR_clock_nanosleep_time64 407 +#define __NR_timer_gettime64 408 +#define __NR_timer_settime64 409 +#define __NR_timerfd_gettime64 410 +#define __NR_timerfd_settime64 411 +#define __NR_utimensat_time64 412 +#define __NR_pselect6_time64 413 +#define __NR_ppoll_time64 414 +#define __NR_io_pgetevents_time64 416 +#define __NR_recvmmsg_time64 417 +#define __NR_mq_timedsend_time64 418 +#define __NR_mq_timedreceive_time64 419 +#define __NR_semtimedop_time64 420 +#define __NR_rt_sigtimedwait_time64 421 +#define __NR_futex_time64 422 +#define __NR_sched_rr_get_interval_time64 423 +#define __NR_pidfd_send_signal 424 +#define __NR_io_uring_setup 425 +#define __NR_io_uring_enter 426 +#define __NR_io_uring_register 427 +#define __NR_open_tree 428 +#define __NR_move_mount 429 +#define __NR_fsopen 430 +#define __NR_fsconfig 431 +#define __NR_fsmount 432 +#define __NR_fspick 433 +#define __NR_pidfd_open 434 +#define __NR_clone3 435 +#define __NR_close_range 436 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 +#define __NR_faccessat2 439 +#define __NR_process_madvise 440 +#define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 +#define __NR_memfd_secret 447 +#define __NR_process_mrelease 448 +#define __NR_futex_waitv 449 +#define __NR_set_mempolicy_home_node 450 +#define __NR_cachestat 451 +#define __NR_fchmodat2 452 +#define __NR_map_shadow_stack 453 +#define __NR_futex_wake 454 +#define __NR_futex_wait 455 +#define __NR_futex_requeue 456 +#define __NR_statmount 457 +#define __NR_listmount 458 +#define __NR_lsm_get_self_attr 459 +#define __NR_lsm_set_self_attr 460 +#define __NR_lsm_list_modules 461 +#define __NR_mseal 462 + + +#endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-riscv/unistd_64.h b/linux-headers/asm-riscv/unistd_64.h new file mode 100644 index 0000000000..95bca8ae81 --- /dev/null +++ b/linux-headers/asm-riscv/unistd_64.h @@ -0,0 +1,325 @@ +#ifndef _ASM_UNISTD_64_H +#define _ASM_UNISTD_64_H + +#define __NR_io_setup 0 +#define __NR_io_destroy 1 +#define __NR_io_submit 2 +#define __NR_io_cancel 3 +#define __NR_io_getevents 4 +#define __NR_setxattr 5 +#define __NR_lsetxattr 6 +#define __NR_fsetxattr 7 +#define __NR_getxattr 8 +#define __NR_lgetxattr 9 +#define __NR_fgetxattr 10 +#define __NR_listxattr 11 +#define __NR_llistxattr 12 +#define __NR_flistxattr 13 +#define __NR_removexattr 14 +#define __NR_lremovexattr 15 +#define __NR_fremovexattr 16 +#define __NR_getcwd 17 +#define __NR_lookup_dcookie 18 +#define __NR_eventfd2 19 +#define __NR_epoll_create1 20 +#define __NR_epoll_ctl 21 +#define __NR_epoll_pwait 22 +#define __NR_dup 23 +#define __NR_dup3 24 +#define __NR_fcntl 25 +#define __NR_inotify_init1 26 +#define __NR_inotify_add_watch 27 +#define __NR_inotify_rm_watch 28 +#define __NR_ioctl 29 +#define __NR_ioprio_set 30 +#define __NR_ioprio_get 31 +#define __NR_flock 32 +#define __NR_mknodat 33 +#define __NR_mkdirat 34 +#define __NR_unlinkat 35 +#define __NR_symlinkat 36 +#define __NR_linkat 37 +#define __NR_umount2 39 +#define __NR_mount 40 +#define __NR_pivot_root 41 +#define __NR_nfsservctl 42 +#define __NR_statfs 43 +#define __NR_fstatfs 44 +#define __NR_truncate 45 +#define __NR_ftruncate 46 +#define __NR_fallocate 47 +#define __NR_faccessat 48 +#define __NR_chdir 49 +#define __NR_fchdir 50 +#define __NR_chroot 51 +#define __NR_fchmod 52 +#define __NR_fchmodat 53 +#define __NR_fchownat 54 +#define __NR_fchown 55 +#define __NR_openat 56 +#define __NR_close 57 +#define __NR_vhangup 58 +#define __NR_pipe2 59 +#define __NR_quotactl 60 +#define __NR_getdents64 61 +#define __NR_lseek 62 +#define __NR_read 63 +#define __NR_write 64 +#define __NR_readv 65 +#define __NR_writev 66 +#define __NR_pread64 67 +#define __NR_pwrite64 68 +#define __NR_preadv 69 +#define __NR_pwritev 70 +#define __NR_sendfile 71 +#define __NR_pselect6 72 +#define __NR_ppoll 73 +#define __NR_signalfd4 74 +#define __NR_vmsplice 75 +#define __NR_splice 76 +#define __NR_tee 77 +#define __NR_readlinkat 78 +#define __NR_newfstatat 79 +#define __NR_fstat 80 +#define __NR_sync 81 +#define __NR_fsync 82 +#define __NR_fdatasync 83 +#define __NR_sync_file_range 84 +#define __NR_timerfd_create 85 +#define __NR_timerfd_settime 86 +#define __NR_timerfd_gettime 87 +#define __NR_utimensat 88 +#define __NR_acct 89 +#define __NR_capget 90 +#define __NR_capset 91 +#define __NR_personality 92 +#define __NR_exit 93 +#define __NR_exit_group 94 +#define __NR_waitid 95 +#define __NR_set_tid_address 96 +#define __NR_unshare 97 +#define __NR_futex 98 +#define __NR_set_robust_list 99 +#define __NR_get_robust_list 100 +#define __NR_nanosleep 101 +#define __NR_getitimer 102 +#define __NR_setitimer 103 +#define __NR_kexec_load 104 +#define __NR_init_module 105 +#define __NR_delete_module 106 +#define __NR_timer_create 107 +#define __NR_timer_gettime 108 +#define __NR_timer_getoverrun 109 +#define __NR_timer_settime 110 +#define __NR_timer_delete 111 +#define __NR_clock_settime 112 +#define __NR_clock_gettime 113 +#define __NR_clock_getres 114 +#define __NR_clock_nanosleep 115 +#define __NR_syslog 116 +#define __NR_ptrace 117 +#define __NR_sched_setparam 118 +#define __NR_sched_setscheduler 119 +#define __NR_sched_getscheduler 120 +#define __NR_sched_getparam 121 +#define __NR_sched_setaffinity 122 +#define __NR_sched_getaffinity 123 +#define __NR_sched_yield 124 +#define __NR_sched_get_priority_max 125 +#define __NR_sched_get_priority_min 126 +#define __NR_sched_rr_get_interval 127 +#define __NR_restart_syscall 128 +#define __NR_kill 129 +#define __NR_tkill 130 +#define __NR_tgkill 131 +#define __NR_sigaltstack 132 +#define __NR_rt_sigsuspend 133 +#define __NR_rt_sigaction 134 +#define __NR_rt_sigprocmask 135 +#define __NR_rt_sigpending 136 +#define __NR_rt_sigtimedwait 137 +#define __NR_rt_sigqueueinfo 138 +#define __NR_rt_sigreturn 139 +#define __NR_setpriority 140 +#define __NR_getpriority 141 +#define __NR_reboot 142 +#define __NR_setregid 143 +#define __NR_setgid 144 +#define __NR_setreuid 145 +#define __NR_setuid 146 +#define __NR_setresuid 147 +#define __NR_getresuid 148 +#define __NR_setresgid 149 +#define __NR_getresgid 150 +#define __NR_setfsuid 151 +#define __NR_setfsgid 152 +#define __NR_times 153 +#define __NR_setpgid 154 +#define __NR_getpgid 155 +#define __NR_getsid 156 +#define __NR_setsid 157 +#define __NR_getgroups 158 +#define __NR_setgroups 159 +#define __NR_uname 160 +#define __NR_sethostname 161 +#define __NR_setdomainname 162 +#define __NR_getrlimit 163 +#define __NR_setrlimit 164 +#define __NR_getrusage 165 +#define __NR_umask 166 +#define __NR_prctl 167 +#define __NR_getcpu 168 +#define __NR_gettimeofday 169 +#define __NR_settimeofday 170 +#define __NR_adjtimex 171 +#define __NR_getpid 172 +#define __NR_getppid 173 +#define __NR_getuid 174 +#define __NR_geteuid 175 +#define __NR_getgid 176 +#define __NR_getegid 177 +#define __NR_gettid 178 +#define __NR_sysinfo 179 +#define __NR_mq_open 180 +#define __NR_mq_unlink 181 +#define __NR_mq_timedsend 182 +#define __NR_mq_timedreceive 183 +#define __NR_mq_notify 184 +#define __NR_mq_getsetattr 185 +#define __NR_msgget 186 +#define __NR_msgctl 187 +#define __NR_msgrcv 188 +#define __NR_msgsnd 189 +#define __NR_semget 190 +#define __NR_semctl 191 +#define __NR_semtimedop 192 +#define __NR_semop 193 +#define __NR_shmget 194 +#define __NR_shmctl 195 +#define __NR_shmat 196 +#define __NR_shmdt 197 +#define __NR_socket 198 +#define __NR_socketpair 199 +#define __NR_bind 200 +#define __NR_listen 201 +#define __NR_accept 202 +#define __NR_connect 203 +#define __NR_getsockname 204 +#define __NR_getpeername 205 +#define __NR_sendto 206 +#define __NR_recvfrom 207 +#define __NR_setsockopt 208 +#define __NR_getsockopt 209 +#define __NR_shutdown 210 +#define __NR_sendmsg 211 +#define __NR_recvmsg 212 +#define __NR_readahead 213 +#define __NR_brk 214 +#define __NR_munmap 215 +#define __NR_mremap 216 +#define __NR_add_key 217 +#define __NR_request_key 218 +#define __NR_keyctl 219 +#define __NR_clone 220 +#define __NR_execve 221 +#define __NR_mmap 222 +#define __NR_fadvise64 223 +#define __NR_swapon 224 +#define __NR_swapoff 225 +#define __NR_mprotect 226 +#define __NR_msync 227 +#define __NR_mlock 228 +#define __NR_munlock 229 +#define __NR_mlockall 230 +#define __NR_munlockall 231 +#define __NR_mincore 232 +#define __NR_madvise 233 +#define __NR_remap_file_pages 234 +#define __NR_mbind 235 +#define __NR_get_mempolicy 236 +#define __NR_set_mempolicy 237 +#define __NR_migrate_pages 238 +#define __NR_move_pages 239 +#define __NR_rt_tgsigqueueinfo 240 +#define __NR_perf_event_open 241 +#define __NR_accept4 242 +#define __NR_recvmmsg 243 +#define __NR_riscv_hwprobe 258 +#define __NR_riscv_flush_icache 259 +#define __NR_wait4 260 +#define __NR_prlimit64 261 +#define __NR_fanotify_init 262 +#define __NR_fanotify_mark 263 +#define __NR_name_to_handle_at 264 +#define __NR_open_by_handle_at 265 +#define __NR_clock_adjtime 266 +#define __NR_syncfs 267 +#define __NR_setns 268 +#define __NR_sendmmsg 269 +#define __NR_process_vm_readv 270 +#define __NR_process_vm_writev 271 +#define __NR_kcmp 272 +#define __NR_finit_module 273 +#define __NR_sched_setattr 274 +#define __NR_sched_getattr 275 +#define __NR_renameat2 276 +#define __NR_seccomp 277 +#define __NR_getrandom 278 +#define __NR_memfd_create 279 +#define __NR_bpf 280 +#define __NR_execveat 281 +#define __NR_userfaultfd 282 +#define __NR_membarrier 283 +#define __NR_mlock2 284 +#define __NR_copy_file_range 285 +#define __NR_preadv2 286 +#define __NR_pwritev2 287 +#define __NR_pkey_mprotect 288 +#define __NR_pkey_alloc 289 +#define __NR_pkey_free 290 +#define __NR_statx 291 +#define __NR_io_pgetevents 292 +#define __NR_rseq 293 +#define __NR_kexec_file_load 294 +#define __NR_pidfd_send_signal 424 +#define __NR_io_uring_setup 425 +#define __NR_io_uring_enter 426 +#define __NR_io_uring_register 427 +#define __NR_open_tree 428 +#define __NR_move_mount 429 +#define __NR_fsopen 430 +#define __NR_fsconfig 431 +#define __NR_fsmount 432 +#define __NR_fspick 433 +#define __NR_pidfd_open 434 +#define __NR_clone3 435 +#define __NR_close_range 436 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 +#define __NR_faccessat2 439 +#define __NR_process_madvise 440 +#define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 +#define __NR_memfd_secret 447 +#define __NR_process_mrelease 448 +#define __NR_futex_waitv 449 +#define __NR_set_mempolicy_home_node 450 +#define __NR_cachestat 451 +#define __NR_fchmodat2 452 +#define __NR_map_shadow_stack 453 +#define __NR_futex_wake 454 +#define __NR_futex_wait 455 +#define __NR_futex_requeue 456 +#define __NR_statmount 457 +#define __NR_listmount 458 +#define __NR_lsm_get_self_attr 459 +#define __NR_lsm_set_self_attr 460 +#define __NR_lsm_list_modules 461 +#define __NR_mseal 462 + + +#endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index 1c8f918234..4711ef2c3d 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -106,6 +106,7 @@ struct kvm_ioapic_state { #define KVM_RUN_X86_SMM (1 << 0) #define KVM_RUN_X86_BUS_LOCK (1 << 1) +#define KVM_RUN_X86_GUEST_MODE (1 << 2) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -436,6 +437,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) +#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h index da439afee1..24c979be54 100644 --- a/linux-headers/asm-x86/unistd_64.h +++ b/linux-headers/asm-x86/unistd_64.h @@ -336,6 +336,7 @@ #define __NR_statx 332 #define __NR_io_pgetevents 333 #define __NR_rseq 334 +#define __NR_uretprobe 335 #define __NR_pidfd_send_signal 424 #define __NR_io_uring_setup 425 #define __NR_io_uring_enter 426 diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h index 4fcb607c72..c23dd21a2d 100644 --- a/linux-headers/asm-x86/unistd_x32.h +++ b/linux-headers/asm-x86/unistd_x32.h @@ -289,6 +289,7 @@ #define __NR_statx (__X32_SYSCALL_BIT + 332) #define __NR_io_pgetevents (__X32_SYSCALL_BIT + 333) #define __NR_rseq (__X32_SYSCALL_BIT + 334) +#define __NR_uretprobe (__X32_SYSCALL_BIT + 335) #define __NR_pidfd_send_signal (__X32_SYSCALL_BIT + 424) #define __NR_io_uring_setup (__X32_SYSCALL_BIT + 425) #define __NR_io_uring_enter (__X32_SYSCALL_BIT + 426) diff --git a/linux-headers/linux/bits.h b/linux-headers/linux/bits.h index d9897771be..c0d00c0a98 100644 --- a/linux-headers/linux/bits.h +++ b/linux-headers/linux/bits.h @@ -12,4 +12,7 @@ (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) + #endif /* _LINUX_BITS_H */ diff --git a/linux-headers/linux/const.h b/linux-headers/linux/const.h index 1eb84b5087..2122610de7 100644 --- a/linux-headers/linux/const.h +++ b/linux-headers/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing __asm__ support + * + * __BIT128() would not work in the __asm__ code, as it shifts an + * 'unsigned __init128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting __asm__ code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h index 72e8f4b9dd..782baf477f 100644 --- a/linux-headers/linux/iommufd.h +++ b/linux-headers/linux/iommufd.h @@ -4,8 +4,8 @@ #ifndef _IOMMUFD_H #define _IOMMUFD_H -#include <linux/types.h> #include <linux/ioctl.h> +#include <linux/types.h> #define IOMMUFD_TYPE (';') @@ -37,19 +37,20 @@ enum { IOMMUFD_CMD_BASE = 0x80, IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE, - IOMMUFD_CMD_IOAS_ALLOC, - IOMMUFD_CMD_IOAS_ALLOW_IOVAS, - IOMMUFD_CMD_IOAS_COPY, - IOMMUFD_CMD_IOAS_IOVA_RANGES, - IOMMUFD_CMD_IOAS_MAP, - IOMMUFD_CMD_IOAS_UNMAP, - IOMMUFD_CMD_OPTION, - IOMMUFD_CMD_VFIO_IOAS, - IOMMUFD_CMD_HWPT_ALLOC, - IOMMUFD_CMD_GET_HW_INFO, - IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, - IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, - IOMMUFD_CMD_HWPT_INVALIDATE, + IOMMUFD_CMD_IOAS_ALLOC = 0x81, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS = 0x82, + IOMMUFD_CMD_IOAS_COPY = 0x83, + IOMMUFD_CMD_IOAS_IOVA_RANGES = 0x84, + IOMMUFD_CMD_IOAS_MAP = 0x85, + IOMMUFD_CMD_IOAS_UNMAP = 0x86, + IOMMUFD_CMD_OPTION = 0x87, + IOMMUFD_CMD_VFIO_IOAS = 0x88, + IOMMUFD_CMD_HWPT_ALLOC = 0x89, + IOMMUFD_CMD_GET_HW_INFO = 0x8a, + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING = 0x8b, + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP = 0x8c, + IOMMUFD_CMD_HWPT_INVALIDATE = 0x8d, + IOMMUFD_CMD_FAULT_QUEUE_ALLOC = 0x8e, }; /** @@ -356,10 +357,13 @@ struct iommu_vfio_ioas { * the parent HWPT in a nesting configuration. * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is * enforced on device attachment + * @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is + * valid. */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, + IOMMU_HWPT_FAULT_ID_VALID = 1 << 2, }; /** @@ -396,8 +400,8 @@ struct iommu_hwpt_vtd_s1 { * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table */ enum iommu_hwpt_data_type { - IOMMU_HWPT_DATA_NONE, - IOMMU_HWPT_DATA_VTD_S1, + IOMMU_HWPT_DATA_NONE = 0, + IOMMU_HWPT_DATA_VTD_S1 = 1, }; /** @@ -411,6 +415,9 @@ enum iommu_hwpt_data_type { * @data_type: One of enum iommu_hwpt_data_type * @data_len: Length of the type specific data * @data_uptr: User pointer to the type specific data + * @fault_id: The ID of IOMMUFD_FAULT object. Valid only if flags field of + * IOMMU_HWPT_FAULT_ID_VALID is set. + * @__reserved2: Padding to 64-bit alignment. Must be 0. * * Explicitly allocate a hardware page table object. This is the same object * type that is returned by iommufd_device_attach() and represents the @@ -441,6 +448,8 @@ struct iommu_hwpt_alloc { __u32 data_type; __u32 data_len; __aligned_u64 data_uptr; + __u32 fault_id; + __u32 __reserved2; }; #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) @@ -482,8 +491,8 @@ struct iommu_hw_info_vtd { * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type */ enum iommu_hw_info_type { - IOMMU_HW_INFO_TYPE_NONE, - IOMMU_HW_INFO_TYPE_INTEL_VTD, + IOMMU_HW_INFO_TYPE_NONE = 0, + IOMMU_HW_INFO_TYPE_INTEL_VTD = 1, }; /** @@ -620,7 +629,7 @@ struct iommu_hwpt_get_dirty_bitmap { * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1 */ enum iommu_hwpt_invalidate_data_type { - IOMMU_HWPT_INVALIDATE_DATA_VTD_S1, + IOMMU_HWPT_INVALIDATE_DATA_VTD_S1 = 0, }; /** @@ -692,4 +701,100 @@ struct iommu_hwpt_invalidate { __u32 __reserved; }; #define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE) + +/** + * enum iommu_hwpt_pgfault_flags - flags for struct iommu_hwpt_pgfault + * @IOMMU_PGFAULT_FLAGS_PASID_VALID: The pasid field of the fault data is + * valid. + * @IOMMU_PGFAULT_FLAGS_LAST_PAGE: It's the last fault of a fault group. + */ +enum iommu_hwpt_pgfault_flags { + IOMMU_PGFAULT_FLAGS_PASID_VALID = (1 << 0), + IOMMU_PGFAULT_FLAGS_LAST_PAGE = (1 << 1), +}; + +/** + * enum iommu_hwpt_pgfault_perm - perm bits for struct iommu_hwpt_pgfault + * @IOMMU_PGFAULT_PERM_READ: request for read permission + * @IOMMU_PGFAULT_PERM_WRITE: request for write permission + * @IOMMU_PGFAULT_PERM_EXEC: (PCIE 10.4.1) request with a PASID that has the + * Execute Requested bit set in PASID TLP Prefix. + * @IOMMU_PGFAULT_PERM_PRIV: (PCIE 10.4.1) request with a PASID that has the + * Privileged Mode Requested bit set in PASID TLP + * Prefix. + */ +enum iommu_hwpt_pgfault_perm { + IOMMU_PGFAULT_PERM_READ = (1 << 0), + IOMMU_PGFAULT_PERM_WRITE = (1 << 1), + IOMMU_PGFAULT_PERM_EXEC = (1 << 2), + IOMMU_PGFAULT_PERM_PRIV = (1 << 3), +}; + +/** + * struct iommu_hwpt_pgfault - iommu page fault data + * @flags: Combination of enum iommu_hwpt_pgfault_flags + * @dev_id: id of the originated device + * @pasid: Process Address Space ID + * @grpid: Page Request Group Index + * @perm: Combination of enum iommu_hwpt_pgfault_perm + * @addr: Fault address + * @length: a hint of how much data the requestor is expecting to fetch. For + * example, if the PRI initiator knows it is going to do a 10MB + * transfer, it could fill in 10MB and the OS could pre-fault in + * 10MB of IOVA. It's default to 0 if there's no such hint. + * @cookie: kernel-managed cookie identifying a group of fault messages. The + * cookie number encoded in the last page fault of the group should + * be echoed back in the response message. + */ +struct iommu_hwpt_pgfault { + __u32 flags; + __u32 dev_id; + __u32 pasid; + __u32 grpid; + __u32 perm; + __u64 addr; + __u32 length; + __u32 cookie; +}; + +/** + * enum iommufd_page_response_code - Return status of fault handlers + * @IOMMUFD_PAGE_RESP_SUCCESS: Fault has been handled and the page tables + * populated, retry the access. This is the + * "Success" defined in PCI 10.4.2.1. + * @IOMMUFD_PAGE_RESP_INVALID: Could not handle this fault, don't retry the + * access. This is the "Invalid Request" in PCI + * 10.4.2.1. + */ +enum iommufd_page_response_code { + IOMMUFD_PAGE_RESP_SUCCESS = 0, + IOMMUFD_PAGE_RESP_INVALID = 1, +}; + +/** + * struct iommu_hwpt_page_response - IOMMU page fault response + * @cookie: The kernel-managed cookie reported in the fault message. + * @code: One of response code in enum iommufd_page_response_code. + */ +struct iommu_hwpt_page_response { + __u32 cookie; + __u32 code; +}; + +/** + * struct iommu_fault_alloc - ioctl(IOMMU_FAULT_QUEUE_ALLOC) + * @size: sizeof(struct iommu_fault_alloc) + * @flags: Must be 0 + * @out_fault_id: The ID of the new FAULT + * @out_fault_fd: The fd of the new FAULT + * + * Explicitly allocate a fault handling object. + */ +struct iommu_fault_alloc { + __u32 size; + __u32 flags; + __u32 out_fault_id; + __u32 out_fault_fd; +}; +#define IOMMU_FAULT_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_FAULT_QUEUE_ALLOC) #endif diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index c93876ca0b..49dd1b30ce 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -192,11 +192,20 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ @@ -913,6 +922,9 @@ struct kvm_enable_cap { #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 +#define KVM_CAP_X86_GUEST_MODE 238 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1544,4 +1556,13 @@ struct kvm_create_guest_memfd { __u64 reserved[6]; }; +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; + __u64 padding[5]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/linux-headers/linux/mman.h b/linux-headers/linux/mman.h index 4e8cb60780..2b83059586 100644 --- a/linux-headers/linux/mman.h +++ b/linux-headers/linux/mman.h @@ -17,6 +17,7 @@ #define MAP_SHARED 0x01 /* Share changes */ #define MAP_PRIVATE 0x02 /* Changes are private */ #define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page diff --git a/linux-headers/linux/psp-sev.h b/linux-headers/linux/psp-sev.h index c3046c6bff..17bf191573 100644 --- a/linux-headers/linux/psp-sev.h +++ b/linux-headers/linux/psp-sev.h @@ -31,6 +31,7 @@ enum { SNP_PLATFORM_STATUS, SNP_COMMIT, SNP_SET_CONFIG, + SNP_VLEK_LOAD, SEV_MAX, }; @@ -50,6 +51,7 @@ typedef enum { SEV_RET_INVALID_PLATFORM_STATE, SEV_RET_INVALID_GUEST_STATE, SEV_RET_INAVLID_CONFIG, + SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, SEV_RET_INVALID_LEN, SEV_RET_ALREADY_OWNED, SEV_RET_INVALID_CERTIFICATE, @@ -215,6 +217,32 @@ struct sev_user_data_snp_config { } __attribute__((packed)); /** + * struct sev_data_snp_vlek_load - SNP_VLEK_LOAD structure + * + * @len: length of the command buffer read by the PSP + * @vlek_wrapped_version: version of wrapped VLEK hashstick (Must be 0h) + * @rsvd: reserved + * @vlek_wrapped_address: address of a wrapped VLEK hashstick + * (struct sev_user_data_snp_wrapped_vlek_hashstick) + */ +struct sev_user_data_snp_vlek_load { + __u32 len; /* In */ + __u8 vlek_wrapped_version; /* In */ + __u8 rsvd[3]; /* In */ + __u64 vlek_wrapped_address; /* In */ +} __attribute__((packed)); + +/** + * struct sev_user_data_snp_vlek_wrapped_vlek_hashstick - Wrapped VLEK data + * + * @data: Opaque data provided by AMD KDS (as described in SEV-SNP Firmware ABI + * 1.54, SNP_VLEK_LOAD) + */ +struct sev_user_data_snp_wrapped_vlek_hashstick { + __u8 data[432]; /* In */ +} __attribute__((packed)); + +/** * struct sev_issue_cmd - SEV ioctl parameters * * @cmd: SEV commands to execute diff --git a/migration/colo.c b/migration/colo.c index 6449490221..9590f281d0 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -935,7 +935,8 @@ void coroutine_fn colo_incoming_co(void) assert(bql_locked()); assert(migration_incoming_colo_enabled()); - qemu_thread_create(&th, "mig/dst/colo", colo_process_incoming_thread, + qemu_thread_create(&th, MIGRATION_THREAD_DST_COLO, + colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE); mis->colo_incoming_co = qemu_coroutine_self(); diff --git a/system/cpu-throttle.c b/migration/cpu-throttle.c index 7632dc6143..5179019e33 100644 --- a/system/cpu-throttle.c +++ b/migration/cpu-throttle.c @@ -28,16 +28,23 @@ #include "qemu/main-loop.h" #include "sysemu/cpus.h" #include "sysemu/cpu-throttle.h" +#include "migration.h" +#include "migration-stats.h" #include "trace.h" /* vcpu throttling controls */ -static QEMUTimer *throttle_timer; +static QEMUTimer *throttle_timer, *throttle_dirty_sync_timer; static unsigned int throttle_percentage; +static bool throttle_dirty_sync_timer_active; +static uint64_t throttle_dirty_sync_count_prev; #define CPU_THROTTLE_PCT_MIN 1 #define CPU_THROTTLE_PCT_MAX 99 #define CPU_THROTTLE_TIMESLICE_NS 10000000 +/* Making sure RAMBlock dirty bitmap is synchronized every five seconds */ +#define CPU_THROTTLE_DIRTY_SYNC_TIMESLICE_MS 5000 + static void cpu_throttle_thread(CPUState *cpu, run_on_cpu_data opaque) { double pct; @@ -112,6 +119,7 @@ void cpu_throttle_set(int new_throttle_pct) void cpu_throttle_stop(void) { qatomic_set(&throttle_percentage, 0); + cpu_throttle_dirty_sync_timer(false); } bool cpu_throttle_active(void) @@ -124,8 +132,68 @@ int cpu_throttle_get_percentage(void) return qatomic_read(&throttle_percentage); } +void cpu_throttle_dirty_sync_timer_tick(void *opaque) +{ + uint64_t sync_cnt = stat64_get(&mig_stats.dirty_sync_count); + + /* + * The first iteration copies all memory anyhow and has no + * effect on guest performance, therefore omit it to avoid + * paying extra for the sync penalty. + */ + if (sync_cnt <= 1) { + goto end; + } + + if (sync_cnt == throttle_dirty_sync_count_prev) { + trace_cpu_throttle_dirty_sync(); + WITH_RCU_READ_LOCK_GUARD() { + migration_bitmap_sync_precopy(false); + } + } + +end: + throttle_dirty_sync_count_prev = stat64_get(&mig_stats.dirty_sync_count); + + timer_mod(throttle_dirty_sync_timer, + qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL_RT) + + CPU_THROTTLE_DIRTY_SYNC_TIMESLICE_MS); +} + +static bool cpu_throttle_dirty_sync_active(void) +{ + return qatomic_read(&throttle_dirty_sync_timer_active); +} + +void cpu_throttle_dirty_sync_timer(bool enable) +{ + assert(throttle_dirty_sync_timer); + + if (enable) { + if (!cpu_throttle_dirty_sync_active()) { + /* + * Always reset the dirty sync count cache, in case migration + * was cancelled once. + */ + throttle_dirty_sync_count_prev = 0; + timer_mod(throttle_dirty_sync_timer, + qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL_RT) + + CPU_THROTTLE_DIRTY_SYNC_TIMESLICE_MS); + qatomic_set(&throttle_dirty_sync_timer_active, 1); + } + } else { + if (cpu_throttle_dirty_sync_active()) { + timer_del(throttle_dirty_sync_timer); + qatomic_set(&throttle_dirty_sync_timer_active, 0); + } + } +} + void cpu_throttle_init(void) { throttle_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT, cpu_throttle_timer_tick, NULL); + throttle_dirty_sync_timer = + timer_new_ms(QEMU_CLOCK_VIRTUAL_RT, + cpu_throttle_dirty_sync_timer_tick, NULL); } diff --git a/migration/dirtyrate.c b/migration/dirtyrate.c index 233acb0855..f7e86686fc 100644 --- a/migration/dirtyrate.c +++ b/migration/dirtyrate.c @@ -29,6 +29,7 @@ #include "sysemu/runstate.h" #include "exec/memory.h" #include "qemu/xxhash.h" +#include "migration.h" /* * total_dirty_pages is procted by BQL and is used @@ -436,6 +437,7 @@ static void get_ramblock_dirty_info(RAMBlock *block, struct DirtyRateConfig *config) { uint64_t sample_pages_per_gigabytes = config->sample_pages_per_gigabytes; + gsize len; /* Right shift 30 bits to calc ramblock size in GB */ info->sample_pages_count = (qemu_ram_get_used_length(block) * @@ -444,7 +446,9 @@ static void get_ramblock_dirty_info(RAMBlock *block, info->ramblock_pages = qemu_ram_get_used_length(block) >> qemu_target_page_bits(); info->ramblock_addr = qemu_ram_get_host_addr(block); - strcpy(info->idstr, qemu_ram_get_idstr(block)); + len = g_strlcpy(info->idstr, qemu_ram_get_idstr(block), + sizeof(info->idstr)); + g_assert(len < sizeof(info->idstr)); } static void free_ramblock_dirty_info(struct RamblockDirtyInfo *infos, int count) @@ -839,8 +843,9 @@ void qmp_calc_dirty_rate(int64_t calc_time, init_dirtyrate_stat(config); - qemu_thread_create(&thread, "get_dirtyrate", get_dirtyrate_thread, - (void *)&config, QEMU_THREAD_DETACHED); + qemu_thread_create(&thread, MIGRATION_THREAD_DIRTY_RATE, + get_dirtyrate_thread, (void *)&config, + QEMU_THREAD_DETACHED); } diff --git a/migration/meson.build b/migration/meson.build index 66d3de86f0..d53cf3417a 100644 --- a/migration/meson.build +++ b/migration/meson.build @@ -13,6 +13,7 @@ system_ss.add(files( 'block-dirty-bitmap.c', 'channel.c', 'channel-block.c', + 'cpu-throttle.c', 'dirtyrate.c', 'exec.c', 'fd.c', diff --git a/migration/migration.c b/migration/migration.c index 021faee2f3..aedf7f0751 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -263,6 +263,9 @@ void migration_object_init(void) ram_mig_init(); dirty_bitmap_mig_init(); + + /* Initialize cpu throttle timers */ + cpu_throttle_init(); } typedef struct { @@ -1110,33 +1113,6 @@ void migrate_send_rp_resume_ack(MigrationIncomingState *mis, uint32_t value) migrate_send_rp_message(mis, MIG_RP_MSG_RESUME_ACK, sizeof(buf), &buf); } -/* - * Return true if we're already in the middle of a migration - * (i.e. any of the active or setup states) - */ -bool migration_is_setup_or_active(void) -{ - MigrationState *s = current_migration; - - switch (s->state) { - case MIGRATION_STATUS_ACTIVE: - case MIGRATION_STATUS_POSTCOPY_ACTIVE: - case MIGRATION_STATUS_POSTCOPY_PAUSED: - case MIGRATION_STATUS_POSTCOPY_RECOVER_SETUP: - case MIGRATION_STATUS_POSTCOPY_RECOVER: - case MIGRATION_STATUS_SETUP: - case MIGRATION_STATUS_PRE_SWITCHOVER: - case MIGRATION_STATUS_DEVICE: - case MIGRATION_STATUS_WAIT_UNPLUG: - case MIGRATION_STATUS_COLO: - return true; - - default: - return false; - - } -} - bool migration_is_running(void) { MigrationState *s = current_migration; @@ -1152,11 +1128,10 @@ bool migration_is_running(void) case MIGRATION_STATUS_DEVICE: case MIGRATION_STATUS_WAIT_UNPLUG: case MIGRATION_STATUS_CANCELLING: + case MIGRATION_STATUS_COLO: return true; - default: return false; - } } @@ -1405,6 +1380,9 @@ void migrate_set_state(MigrationStatus *state, MigrationStatus old_state, static void migrate_fd_cleanup(MigrationState *s) { MigrationEventType type; + QEMUFile *tmp = NULL; + + trace_migrate_fd_cleanup(); g_free(s->hostname); s->hostname = NULL; @@ -1415,26 +1393,29 @@ static void migrate_fd_cleanup(MigrationState *s) close_return_path_on_source(s); - if (s->to_dst_file) { - QEMUFile *tmp; - - trace_migrate_fd_cleanup(); + if (s->migration_thread_running) { bql_unlock(); - if (s->migration_thread_running) { - qemu_thread_join(&s->thread); - s->migration_thread_running = false; - } + qemu_thread_join(&s->thread); + s->migration_thread_running = false; bql_lock(); + } - multifd_send_shutdown(); - qemu_mutex_lock(&s->qemu_file_lock); + WITH_QEMU_LOCK_GUARD(&s->qemu_file_lock) { + /* + * Close the file handle without the lock to make sure the critical + * section won't block for long. + */ tmp = s->to_dst_file; s->to_dst_file = NULL; - qemu_mutex_unlock(&s->qemu_file_lock); + } + + if (tmp) { /* - * Close the file handle without the lock to make sure the - * critical section won't block for long. + * We only need to shutdown multifd if tmp!=NULL, because if + * tmp==NULL, it means the main channel isn't established, while + * multifd is only setup after that (in migration_thread()). */ + multifd_send_shutdown(); migration_ioc_unregister_yank_from_file(tmp); qemu_fclose(tmp); } @@ -1649,27 +1630,7 @@ bool migration_incoming_postcopy_advised(void) bool migration_in_bg_snapshot(void) { - return migrate_background_snapshot() && - migration_is_setup_or_active(); -} - -bool migration_is_idle(void) -{ - MigrationState *s = current_migration; - - if (!s) { - return true; - } - - switch (s->state) { - case MIGRATION_STATUS_NONE: - case MIGRATION_STATUS_CANCELLED: - case MIGRATION_STATUS_COMPLETED: - case MIGRATION_STATUS_FAILED: - return true; - default: - return false; - } + return migrate_background_snapshot() && migration_is_running(); } bool migration_is_active(void) @@ -1750,7 +1711,7 @@ static bool is_busy(Error **reasonp, Error **errp) ERRP_GUARD(); /* Snapshots are similar to migrations, so check RUN_STATE_SAVE_VM too. */ - if (runstate_check(RUN_STATE_SAVE_VM) || !migration_is_idle()) { + if (runstate_check(RUN_STATE_SAVE_VM) || migration_is_running()) { error_propagate_prepend(errp, *reasonp, "disallowing migration blocker " "(migration/snapshot in progress) for: "); @@ -2323,7 +2284,7 @@ static void *source_return_path_thread(void *opaque) trace_source_return_path_thread_entry(); rcu_register_thread(); - while (migration_is_setup_or_active()) { + while (migration_is_running()) { trace_source_return_path_thread_loop_top(); header_type = qemu_get_be16(rp); @@ -2478,7 +2439,7 @@ static int open_return_path_on_source(MigrationState *ms) trace_open_return_path_on_source(); - qemu_thread_create(&ms->rp_state.rp_thread, "mig/src/rp-thr", + qemu_thread_create(&ms->rp_state.rp_thread, MIGRATION_THREAD_SRC_RETURN, source_return_path_thread, ms, QEMU_THREAD_JOINABLE); ms->rp_state.rp_thread_created = true; @@ -3288,10 +3249,17 @@ static MigIterateState migration_iteration_run(MigrationState *s) static void migration_iteration_finish(MigrationState *s) { - /* If we enabled cpu throttling for auto-converge, turn it off. */ - cpu_throttle_stop(); - bql_lock(); + + /* + * If we enabled cpu throttling for auto-converge, turn it off. + * Stopping CPU throttle should be serialized by BQL to avoid + * racing for the throttle_dirty_sync_timer. + */ + if (migrate_auto_converge()) { + cpu_throttle_stop(); + } + switch (s->state) { case MIGRATION_STATUS_COMPLETED: runstate_set(RUN_STATE_POSTMIGRATE); @@ -3467,11 +3435,11 @@ static void *migration_thread(void *opaque) Error *local_err = NULL; int ret; - thread = migration_threads_add("live_migration", qemu_get_thread_id()); + thread = migration_threads_add(MIGRATION_THREAD_SRC_MAIN, + qemu_get_thread_id()); rcu_register_thread(); - object_ref(OBJECT(s)); update_iteration_initial_status(s); if (!multifd_send_setup()) { @@ -3508,6 +3476,11 @@ static void *migration_thread(void *opaque) qemu_savevm_send_colo_enable(s->to_dst_file); } + if (migrate_auto_converge()) { + /* Start RAMBlock dirty bitmap sync timer */ + cpu_throttle_dirty_sync_timer(true); + } + bql_lock(); ret = qemu_savevm_state_setup(s->to_dst_file, &local_err); bql_unlock(); @@ -3604,7 +3577,6 @@ static void *bg_migration_thread(void *opaque) int ret; rcu_register_thread(); - object_ref(OBJECT(s)); migration_rate_set(RATE_LIMIT_DISABLED); @@ -3816,11 +3788,19 @@ void migrate_fd_connect(MigrationState *s, Error *error_in) } } + /* + * Take a refcount to make sure the migration object won't get freed by + * the main thread already in migration_shutdown(). + * + * The refcount will be released at the end of the thread function. + */ + object_ref(OBJECT(s)); + if (migrate_background_snapshot()) { - qemu_thread_create(&s->thread, "mig/snapshot", + qemu_thread_create(&s->thread, MIGRATION_THREAD_SNAPSHOT, bg_migration_thread, s, QEMU_THREAD_JOINABLE); } else { - qemu_thread_create(&s->thread, "mig/src/main", + qemu_thread_create(&s->thread, MIGRATION_THREAD_SRC_MAIN, migration_thread, s, QEMU_THREAD_JOINABLE); } s->migration_thread_running = true; diff --git a/migration/migration.h b/migration/migration.h index 38aa1402d5..0956e9274b 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -28,6 +28,20 @@ #include "sysemu/runstate.h" #include "migration/misc.h" +#define MIGRATION_THREAD_SNAPSHOT "mig/snapshot" +#define MIGRATION_THREAD_DIRTY_RATE "mig/dirtyrate" + +#define MIGRATION_THREAD_SRC_MAIN "mig/src/main" +#define MIGRATION_THREAD_SRC_MULTIFD "mig/src/send_%d" +#define MIGRATION_THREAD_SRC_RETURN "mig/src/return" +#define MIGRATION_THREAD_SRC_TLS "mig/src/tls" + +#define MIGRATION_THREAD_DST_COLO "mig/dst/colo" +#define MIGRATION_THREAD_DST_MULTIFD "mig/src/recv_%d" +#define MIGRATION_THREAD_DST_FAULT "mig/dst/fault" +#define MIGRATION_THREAD_DST_LISTEN "mig/dst/listen" +#define MIGRATION_THREAD_DST_PREEMPT "mig/dst/preempt" + struct PostcopyBlocktimeContext; #define MIGRATION_RESUME_ACK_VALUE (1) @@ -537,4 +551,9 @@ int migration_rp_wait(MigrationState *s); */ void migration_rp_kick(MigrationState *s); +void migration_bitmap_sync_precopy(bool last_stage); + +/* migration/block-dirty-bitmap.c */ +void dirty_bitmap_mig_init(void); + #endif diff --git a/migration/multifd.c b/migration/multifd.c index 9b200f4ad9..4374e14a96 100644 --- a/migration/multifd.c +++ b/migration/multifd.c @@ -600,6 +600,7 @@ static void *multifd_send_thread(void *opaque) * qatomic_store_release() in multifd_send(). */ if (qatomic_load_acquire(&p->pending_job)) { + p->flags = 0; p->iovs_num = 0; assert(!multifd_payload_empty(p->data)); @@ -651,7 +652,6 @@ static void *multifd_send_thread(void *opaque) } /* p->next_packet_size will always be zero for a SYNC packet */ stat64_add(&mig_stats.multifd_bytes, p->packet_len); - p->flags = 0; } qatomic_set(&p->pending_sync, false); @@ -723,7 +723,7 @@ static bool multifd_tls_channel_connect(MultiFDSendParams *p, args->p = p; p->tls_thread_created = true; - qemu_thread_create(&p->tls_thread, "mig/src/tls", + qemu_thread_create(&p->tls_thread, MIGRATION_THREAD_SRC_TLS, multifd_tls_handshake_thread, args, QEMU_THREAD_JOINABLE); return true; @@ -841,7 +841,7 @@ bool multifd_send_setup(void) + sizeof(uint64_t) * page_count; p->packet = g_malloc0(p->packet_len); } - p->name = g_strdup_printf("mig/src/send_%d", i); + p->name = g_strdup_printf(MIGRATION_THREAD_SRC_MULTIFD, i); p->write_flags = 0; if (!multifd_new_send_channel_create(p, &local_err)) { @@ -1259,7 +1259,7 @@ int multifd_recv_setup(Error **errp) + sizeof(uint64_t) * page_count; p->packet = g_malloc0(p->packet_len); } - p->name = g_strdup_printf("mig/dst/recv_%d", i); + p->name = g_strdup_printf(MIGRATION_THREAD_DST_MULTIFD, i); p->normal = g_new0(ram_addr_t, page_count); p->zero = g_new0(ram_addr_t, page_count); } diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 83f6160a36..a535fd2e30 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -1230,7 +1230,8 @@ int postcopy_ram_incoming_setup(MigrationIncomingState *mis) return -1; } - postcopy_thread_create(mis, &mis->fault_thread, "mig/dst/fault", + postcopy_thread_create(mis, &mis->fault_thread, + MIGRATION_THREAD_DST_FAULT, postcopy_ram_fault_thread, QEMU_THREAD_JOINABLE); mis->have_fault_thread = true; @@ -1250,7 +1251,8 @@ int postcopy_ram_incoming_setup(MigrationIncomingState *mis) * This thread needs to be created after the temp pages because * it'll fetch RAM_CHANNEL_POSTCOPY PostcopyTmpPage immediately. */ - postcopy_thread_create(mis, &mis->postcopy_prio_thread, "mig/dst/preempt", + postcopy_thread_create(mis, &mis->postcopy_prio_thread, + MIGRATION_THREAD_DST_PREEMPT, postcopy_preempt_thread, QEMU_THREAD_JOINABLE); mis->preempt_thread_status = PREEMPT_THREAD_CREATED; } diff --git a/migration/ram.c b/migration/ram.c index 326ce7eb79..05ff9eb328 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -1088,9 +1088,10 @@ static void migration_bitmap_sync(RAMState *rs, bool last_stage) } } -static void migration_bitmap_sync_precopy(RAMState *rs, bool last_stage) +void migration_bitmap_sync_precopy(bool last_stage) { Error *local_err = NULL; + assert(ram_state); /* * The current notifier usage is just an optimization to migration, so we @@ -1101,7 +1102,7 @@ static void migration_bitmap_sync_precopy(RAMState *rs, bool last_stage) local_err = NULL; } - migration_bitmap_sync(rs, last_stage); + migration_bitmap_sync(ram_state, last_stage); if (precopy_notify(PRECOPY_NOTIFY_AFTER_BITMAP_SYNC, &local_err)) { error_report_err(local_err); @@ -2782,7 +2783,7 @@ static bool ram_init_bitmaps(RAMState *rs, Error **errp) if (!ret) { goto out_unlock; } - migration_bitmap_sync_precopy(rs, false); + migration_bitmap_sync_precopy(false); } } out_unlock: @@ -2859,7 +2860,7 @@ void qemu_guest_free_page_hint(void *addr, size_t len) size_t used_len, start, npages; /* This function is currently expected to be used during live migration */ - if (!migration_is_setup_or_active()) { + if (!migration_is_running()) { return; } @@ -3207,8 +3208,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) } out: - if (ret >= 0 - && migration_is_setup_or_active()) { + if (ret >= 0 && migration_is_running()) { if (migrate_multifd() && migrate_multifd_flush_after_each_section() && !migrate_mapped_ram()) { ret = multifd_ram_flush_and_sync(); @@ -3248,7 +3248,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque) WITH_RCU_READ_LOCK_GUARD() { if (!migration_in_postcopy()) { - migration_bitmap_sync_precopy(rs, true); + migration_bitmap_sync_precopy(true); } ret = rdma_registration_start(f, RAM_CONTROL_FINISH); @@ -3330,7 +3330,7 @@ static void ram_state_pending_exact(void *opaque, uint64_t *must_precopy, if (!migration_in_postcopy()) { bql_lock(); WITH_RCU_READ_LOCK_GUARD() { - migration_bitmap_sync_precopy(rs, false); + migration_bitmap_sync_precopy(false); } bql_unlock(); } @@ -4294,6 +4294,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) * it will be necessary to reduce the granularity of this * critical section. */ + trace_ram_load_start(); WITH_RCU_READ_LOCK_GUARD() { if (postcopy_running) { /* @@ -4498,7 +4499,7 @@ static void ram_mig_ram_block_resized(RAMBlockNotifier *n, void *host, return; } - if (!migration_is_idle()) { + if (migration_is_running()) { /* * Precopy code on the source cannot deal with the size of RAM blocks * changing at random points in time - especially after sending the diff --git a/migration/ram.h b/migration/ram.h index bc0318b834..0d1981f888 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -44,6 +44,7 @@ extern XBZRLECacheStats xbzrle_counters; INTERNAL_RAMBLOCK_FOREACH(block) \ if (!qemu_ram_is_migratable(block)) {} else +void ram_mig_init(void); int xbzrle_cache_resize(uint64_t new_size, Error **errp); uint64_t ram_bytes_remaining(void); uint64_t ram_bytes_total(void); diff --git a/migration/savevm.c b/migration/savevm.c index 7e1e27182a..e796436979 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -2131,7 +2131,8 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) } mis->have_listen_thread = true; - postcopy_thread_create(mis, &mis->listen_thread, "mig/dst/listen", + postcopy_thread_create(mis, &mis->listen_thread, + MIGRATION_THREAD_DST_LISTEN, postcopy_ram_listen_thread, QEMU_THREAD_DETACHED); trace_loadvm_postcopy_handle_listen("return"); diff --git a/migration/trace-events b/migration/trace-events index c65902f042..bb0e0cc6dc 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -115,6 +115,7 @@ colo_flush_ram_cache_end(void) "" save_xbzrle_page_skipping(void) "" save_xbzrle_page_overflow(void) "" ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRIu64 " milliseconds, %d iterations" +ram_load_start(void) "" ram_load_complete(int ret, uint64_t seq_iter) "exit_code %d seq iteration %" PRIu64 ram_write_tracking_ramblock_start(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu" ram_write_tracking_ramblock_stop(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu" @@ -378,3 +379,7 @@ migration_block_progression(unsigned percent) "Completed %u%%" # page_cache.c migration_pagecache_init(int64_t max_num_items) "Setting cache buckets to %" PRId64 migration_pagecache_insert(void) "Error allocating page" + +# cpu-throttle.c +cpu_throttle_set(int new_throttle_pct) "set guest CPU throttled by %d%%" +cpu_throttle_dirty_sync(void) "" diff --git a/migration/vmstate.c b/migration/vmstate.c index ff5d589a6d..fa002b24e8 100644 --- a/migration/vmstate.c +++ b/migration/vmstate.c @@ -22,7 +22,8 @@ #include "trace.h" static int vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque, JSONWriter *vmdesc); + void *opaque, JSONWriter *vmdesc, + Error **errp); static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, void *opaque); @@ -441,12 +442,13 @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, json_writer_end_array(vmdesc); } - ret = vmstate_subsection_save(f, vmsd, opaque, vmdesc); + ret = vmstate_subsection_save(f, vmsd, opaque, vmdesc, errp); if (vmsd->post_save) { int ps_ret = vmsd->post_save(opaque); - if (!ret) { + if (!ret && ps_ret) { ret = ps_ret; + error_setg(errp, "post-save failed: %s", vmsd->name); } } return ret; @@ -518,7 +520,8 @@ static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, } static int vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque, JSONWriter *vmdesc) + void *opaque, JSONWriter *vmdesc, + Error **errp) { const VMStateDescription * const *sub = vmsd->subsections; bool vmdesc_has_subsections = false; @@ -546,7 +549,7 @@ static int vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, qemu_put_byte(f, len); qemu_put_buffer(f, (uint8_t *)vmsdsub->name, len); qemu_put_be32(f, vmsdsub->version_id); - ret = vmstate_save_state(f, vmsdsub, opaque, vmdesc); + ret = vmstate_save_state_with_err(f, vmsdsub, opaque, vmdesc, errp); if (ret) { return ret; } diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index 46b02c50be..231b45246c 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -375,8 +375,7 @@ static int vhost_vdpa_net_data_start(NetClientState *nc) assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); - if (s->always_svq || - migration_is_setup_or_active()) { + if (s->always_svq || migration_is_running()) { v->shadow_vqs_enabled = true; } else { v->shadow_vqs_enabled = false; diff --git a/pc-bios/hppa-firmware.img b/pc-bios/hppa-firmware.img index e065e48ded..6832dfc06d 100755..100644 --- a/pc-bios/hppa-firmware.img +++ b/pc-bios/hppa-firmware.img Binary files differdiff --git a/pc-bios/hppa-firmware64.img b/pc-bios/hppa-firmware64.img index 7f6d837f0d..16c08aa497 100755..100644 --- a/pc-bios/hppa-firmware64.img +++ b/pc-bios/hppa-firmware64.img Binary files differdiff --git a/qapi/migration.json b/qapi/migration.json index 3af6aa1740..a605dc26db 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -2284,12 +2284,17 @@ # # Returns information of migration threads # +# Features: +# +# @deprecated: This command is deprecated with no replacement yet. +# # Returns: @MigrationThreadInfo # # Since: 7.2 ## { 'command': 'query-migrationthreads', - 'returns': ['MigrationThreadInfo'] } + 'returns': ['MigrationThreadInfo'], + 'features': ['deprecated'] } ## # @snapshot-save: diff --git a/roms/seabios-hppa b/roms/seabios-hppa -Subproject 03774edaad3bfae090ac96ca5450353c641637d +Subproject a528f01d7abd511d3cc71b7acaab6e036ee524b diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index c34ac6454e..99a8d9fa4c 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -163,6 +163,7 @@ EOF fi if [ $arch = arm64 ]; then cp "$hdrdir/include/asm/sve_context.h" "$output/linux-headers/asm-arm64/" + cp "$hdrdir/include/asm/unistd_64.h" "$output/linux-headers/asm-arm64/" fi if [ $arch = x86 ]; then cp "$hdrdir/include/asm/unistd_32.h" "$output/linux-headers/asm-x86/" @@ -185,6 +186,12 @@ EOF fi if [ $arch = riscv ]; then cp "$hdrdir/include/asm/ptrace.h" "$output/linux-headers/asm-riscv/" + cp "$hdrdir/include/asm/unistd_32.h" "$output/linux-headers/asm-riscv/" + cp "$hdrdir/include/asm/unistd_64.h" "$output/linux-headers/asm-riscv/" + fi + if [ $arch = loongarch ]; then + cp "$hdrdir/include/asm/kvm_para.h" "$output/linux-headers/asm-loongarch/" + cp "$hdrdir/include/asm/unistd_64.h" "$output/linux-headers/asm-loongarch/" fi done arch= diff --git a/system/cpu-timers.c b/system/cpu-timers.c index 0b31c9a1b6..856e502e34 100644 --- a/system/cpu-timers.c +++ b/system/cpu-timers.c @@ -35,7 +35,6 @@ #include "sysemu/runstate.h" #include "hw/core/cpu.h" #include "sysemu/cpu-timers.h" -#include "sysemu/cpu-throttle.h" #include "sysemu/cpu-timers-internal.h" /* clock and ticks */ @@ -272,6 +271,4 @@ void cpu_timers_init(void) seqlock_init(&timers_state.vm_clock_seqlock); qemu_spin_init(&timers_state.vm_clock_lock); vmstate_register(NULL, 0, &vmstate_timers, &timers_state); - - cpu_throttle_init(); } diff --git a/system/meson.build b/system/meson.build index a296270cb0..4952f4b2c7 100644 --- a/system/meson.build +++ b/system/meson.build @@ -10,7 +10,6 @@ system_ss.add(files( 'balloon.c', 'bootdevice.c', 'cpus.c', - 'cpu-throttle.c', 'cpu-timers.c', 'datadir.c', 'dirtylimit.c', diff --git a/system/qdev-monitor.c b/system/qdev-monitor.c index 44994ea0e1..320c47b72d 100644 --- a/system/qdev-monitor.c +++ b/system/qdev-monitor.c @@ -679,7 +679,7 @@ DeviceState *qdev_device_add_from_qdict(const QDict *opts, return NULL; } - if (!migration_is_idle()) { + if (migration_is_running()) { error_setg(errp, "device_add not allowed while migrating"); return NULL; } @@ -928,7 +928,7 @@ void qdev_unplug(DeviceState *dev, Error **errp) return; } - if (!migration_is_idle() && !dev->allow_unplug_during_migration) { + if (migration_is_running() && !dev->allow_unplug_during_migration) { error_setg(errp, "device_del not allowed while migrating"); return; } diff --git a/system/trace-events b/system/trace-events index 074d001e90..2ed1d59b1f 100644 --- a/system/trace-events +++ b/system/trace-events @@ -44,6 +44,3 @@ dirtylimit_state_finalize(void) dirtylimit_throttle_pct(int cpu_index, uint64_t pct, int64_t time_us) "CPU[%d] throttle percent: %" PRIu64 ", throttle adjust time %"PRIi64 " us" dirtylimit_set_vcpu(int cpu_index, uint64_t quota) "CPU[%d] set dirty page rate limit %"PRIu64 dirtylimit_vcpu_execute(int cpu_index, int64_t sleep_time_us) "CPU[%d] sleep %"PRIi64 " us" - -# cpu-throttle.c -cpu_throttle_set(int new_throttle_pct) "set guest CPU throttled by %d%%" diff --git a/target/loongarch/cpu.c b/target/loongarch/cpu.c index 7212fb5f8f..57cc4f314b 100644 --- a/target/loongarch/cpu.c +++ b/target/loongarch/cpu.c @@ -664,12 +664,55 @@ static void loongarch_set_lasx(Object *obj, bool value, Error **errp) } } +static bool loongarch_get_lbt(Object *obj, Error **errp) +{ + return LOONGARCH_CPU(obj)->lbt != ON_OFF_AUTO_OFF; +} + +static void loongarch_set_lbt(Object *obj, bool value, Error **errp) +{ + LoongArchCPU *cpu = LOONGARCH_CPU(obj); + + cpu->lbt = value ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF; +} + +static bool loongarch_get_pmu(Object *obj, Error **errp) +{ + return LOONGARCH_CPU(obj)->pmu != ON_OFF_AUTO_OFF; +} + +static void loongarch_set_pmu(Object *obj, bool value, Error **errp) +{ + LoongArchCPU *cpu = LOONGARCH_CPU(obj); + + cpu->pmu = value ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF; +} + void loongarch_cpu_post_init(Object *obj) { + LoongArchCPU *cpu = LOONGARCH_CPU(obj); + object_property_add_bool(obj, "lsx", loongarch_get_lsx, loongarch_set_lsx); object_property_add_bool(obj, "lasx", loongarch_get_lasx, loongarch_set_lasx); + /* lbt is enabled only in kvm mode, not supported in tcg mode */ + if (kvm_enabled()) { + cpu->lbt = ON_OFF_AUTO_AUTO; + object_property_add_bool(obj, "lbt", loongarch_get_lbt, + loongarch_set_lbt); + object_property_set_description(obj, "lbt", + "Set off to disable Binary Tranlation."); + + cpu->pmu = ON_OFF_AUTO_AUTO; + object_property_add_bool(obj, "pmu", loongarch_get_pmu, + loongarch_set_pmu); + object_property_set_description(obj, "pmu", + "Set off to performance monitor unit."); + + } else { + cpu->lbt = ON_OFF_AUTO_OFF; + } } static void loongarch_cpu_init(Object *obj) diff --git a/target/loongarch/cpu.h b/target/loongarch/cpu.h index 6c41fafb70..86c86c6c95 100644 --- a/target/loongarch/cpu.h +++ b/target/loongarch/cpu.h @@ -153,6 +153,7 @@ FIELD(CPUCFG2, LLFTP_VER, 15, 3) FIELD(CPUCFG2, LBT_X86, 18, 1) FIELD(CPUCFG2, LBT_ARM, 19, 1) FIELD(CPUCFG2, LBT_MIPS, 20, 1) +FIELD(CPUCFG2, LBT_ALL, 18, 3) FIELD(CPUCFG2, LSPW, 21, 1) FIELD(CPUCFG2, LAM, 22, 1) @@ -281,6 +282,22 @@ struct LoongArchTLB { typedef struct LoongArchTLB LoongArchTLB; #endif +enum loongarch_features { + LOONGARCH_FEATURE_LBT, /* loongson binary translation extension */ + LOONGARCH_FEATURE_PMU, +}; + +typedef struct LoongArchBT { + /* scratch registers */ + uint64_t scr0; + uint64_t scr1; + uint64_t scr2; + uint64_t scr3; + /* loongarch eflags */ + uint32_t eflags; + uint32_t ftop; +} lbt_t; + typedef struct CPUArchState { uint64_t gpr[32]; uint64_t pc; @@ -288,6 +305,7 @@ typedef struct CPUArchState { fpr_t fpr[32]; bool cf[8]; uint32_t fcsr0; + lbt_t lbt; uint32_t cpucfg[21]; @@ -346,6 +364,9 @@ typedef struct CPUArchState { uint64_t CSR_DBG; uint64_t CSR_DERA; uint64_t CSR_DSAVE; + struct { + uint64_t guest_addr; + } stealtime; #ifdef CONFIG_TCG float_status fp_status; @@ -381,6 +402,8 @@ struct ArchCPU { CPULoongArchState env; QEMUTimer timer; uint32_t phy_id; + OnOffAuto lbt; + OnOffAuto pmu; /* 'compatible' string for this CPU for Linux device trees */ const char *dtb_compatible; diff --git a/target/loongarch/kvm/kvm.c b/target/loongarch/kvm/kvm.c index 30ec16025d..ff81806ca3 100644 --- a/target/loongarch/kvm/kvm.c +++ b/target/loongarch/kvm/kvm.c @@ -9,6 +9,7 @@ #include <sys/ioctl.h> #include <linux/kvm.h> +#include "qapi/error.h" #include "qemu/timer.h" #include "qemu/error-report.h" #include "qemu/main-loop.h" @@ -33,6 +34,55 @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = { KVM_CAP_LAST_INFO }; +static int kvm_get_stealtime(CPUState *cs) +{ + CPULoongArchState *env = cpu_env(cs); + int err; + struct kvm_device_attr attr = { + .group = KVM_LOONGARCH_VCPU_PVTIME_CTRL, + .attr = KVM_LOONGARCH_VCPU_PVTIME_GPA, + .addr = (uint64_t)&env->stealtime.guest_addr, + }; + + err = kvm_vcpu_ioctl(cs, KVM_HAS_DEVICE_ATTR, attr); + if (err) { + return 0; + } + + err = kvm_vcpu_ioctl(cs, KVM_GET_DEVICE_ATTR, attr); + if (err) { + error_report("PVTIME: KVM_GET_DEVICE_ATTR: %s", strerror(errno)); + return err; + } + + return 0; +} + +static int kvm_set_stealtime(CPUState *cs) +{ + CPULoongArchState *env = cpu_env(cs); + int err; + struct kvm_device_attr attr = { + .group = KVM_LOONGARCH_VCPU_PVTIME_CTRL, + .attr = KVM_LOONGARCH_VCPU_PVTIME_GPA, + .addr = (uint64_t)&env->stealtime.guest_addr, + }; + + err = kvm_vcpu_ioctl(cs, KVM_HAS_DEVICE_ATTR, attr); + if (err) { + return 0; + } + + err = kvm_vcpu_ioctl(cs, KVM_SET_DEVICE_ATTR, attr); + if (err) { + error_report("PVTIME: KVM_SET_DEVICE_ATTR %s with gpa "TARGET_FMT_lx, + strerror(errno), env->stealtime.guest_addr); + return err; + } + + return 0; +} + static int kvm_loongarch_get_regs_core(CPUState *cs) { int ret = 0; @@ -476,6 +526,58 @@ static int kvm_loongarch_put_regs_fp(CPUState *cs) return ret; } +static int kvm_loongarch_put_lbt(CPUState *cs) +{ + CPULoongArchState *env = cpu_env(cs); + uint64_t val; + int ret; + + /* check whether vm support LBT firstly */ + if (FIELD_EX32(env->cpucfg[2], CPUCFG2, LBT_ALL) != 7) { + return 0; + } + + /* set six LBT registers including scr0-scr3, eflags, ftop */ + ret = kvm_set_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR0, &env->lbt.scr0); + ret |= kvm_set_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR1, &env->lbt.scr1); + ret |= kvm_set_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR2, &env->lbt.scr2); + ret |= kvm_set_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR3, &env->lbt.scr3); + /* + * Be cautious, KVM_REG_LOONGARCH_LBT_FTOP is defined as 64-bit however + * lbt.ftop is 32-bit; the same with KVM_REG_LOONGARCH_LBT_EFLAGS register + */ + val = env->lbt.eflags; + ret |= kvm_set_one_reg(cs, KVM_REG_LOONGARCH_LBT_EFLAGS, &val); + val = env->lbt.ftop; + ret |= kvm_set_one_reg(cs, KVM_REG_LOONGARCH_LBT_FTOP, &val); + + return ret; +} + +static int kvm_loongarch_get_lbt(CPUState *cs) +{ + CPULoongArchState *env = cpu_env(cs); + uint64_t val; + int ret; + + /* check whether vm support LBT firstly */ + if (FIELD_EX32(env->cpucfg[2], CPUCFG2, LBT_ALL) != 7) { + return 0; + } + + /* get six LBT registers including scr0-scr3, eflags, ftop */ + ret = kvm_get_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR0, &env->lbt.scr0); + ret |= kvm_get_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR1, &env->lbt.scr1); + ret |= kvm_get_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR2, &env->lbt.scr2); + ret |= kvm_get_one_reg(cs, KVM_REG_LOONGARCH_LBT_SCR3, &env->lbt.scr3); + ret |= kvm_get_one_reg(cs, KVM_REG_LOONGARCH_LBT_EFLAGS, &val); + env->lbt.eflags = (uint32_t)val; + ret |= kvm_get_one_reg(cs, KVM_REG_LOONGARCH_LBT_FTOP, &val); + env->lbt.ftop = (uint32_t)val; + + return ret; +} + void kvm_arch_reset_vcpu(CPUState *cs) { CPULoongArchState *env = cpu_env(cs); @@ -612,6 +714,16 @@ int kvm_arch_get_registers(CPUState *cs, Error **errp) return ret; } + ret = kvm_loongarch_get_lbt(cs); + if (ret) { + return ret; + } + + ret = kvm_get_stealtime(cs); + if (ret) { + return ret; + } + ret = kvm_loongarch_get_mpstate(cs); return ret; } @@ -640,6 +752,22 @@ int kvm_arch_put_registers(CPUState *cs, int level, Error **errp) return ret; } + ret = kvm_loongarch_put_lbt(cs); + if (ret) { + return ret; + } + + if (level >= KVM_PUT_FULL_STATE) { + /* + * only KVM_PUT_FULL_STATE is required, kvm kernel will clear + * guest_addr for KVM_PUT_RESET_STATE + */ + ret = kvm_set_stealtime(cs); + if (ret) { + return ret; + } + } + ret = kvm_loongarch_put_mpstate(cs); return ret; } @@ -666,17 +794,112 @@ static void kvm_loongarch_vm_stage_change(void *opaque, bool running, } } +static bool kvm_feature_supported(CPUState *cs, enum loongarch_features feature) +{ + int ret; + struct kvm_device_attr attr; + + switch (feature) { + case LOONGARCH_FEATURE_LBT: + /* + * Return all if all the LBT features are supported such as: + * KVM_LOONGARCH_VM_FEAT_X86BT + * KVM_LOONGARCH_VM_FEAT_ARMBT + * KVM_LOONGARCH_VM_FEAT_MIPSBT + */ + attr.group = KVM_LOONGARCH_VM_FEAT_CTRL; + attr.attr = KVM_LOONGARCH_VM_FEAT_X86BT; + ret = kvm_vm_ioctl(kvm_state, KVM_HAS_DEVICE_ATTR, &attr); + attr.attr = KVM_LOONGARCH_VM_FEAT_ARMBT; + ret |= kvm_vm_ioctl(kvm_state, KVM_HAS_DEVICE_ATTR, &attr); + attr.attr = KVM_LOONGARCH_VM_FEAT_MIPSBT; + ret |= kvm_vm_ioctl(kvm_state, KVM_HAS_DEVICE_ATTR, &attr); + return (ret == 0); + + case LOONGARCH_FEATURE_PMU: + attr.group = KVM_LOONGARCH_VM_FEAT_CTRL; + attr.attr = KVM_LOONGARCH_VM_FEAT_PMU; + ret = kvm_vm_ioctl(kvm_state, KVM_HAS_DEVICE_ATTR, &attr); + return (ret == 0); + + default: + return false; + } + + return false; +} + +static int kvm_cpu_check_lbt(CPUState *cs, Error **errp) +{ + CPULoongArchState *env = cpu_env(cs); + LoongArchCPU *cpu = LOONGARCH_CPU(cs); + bool kvm_supported; + + kvm_supported = kvm_feature_supported(cs, LOONGARCH_FEATURE_LBT); + if (cpu->lbt == ON_OFF_AUTO_ON) { + if (kvm_supported) { + env->cpucfg[2] = FIELD_DP32(env->cpucfg[2], CPUCFG2, LBT_ALL, 7); + } else { + error_setg(errp, "'lbt' feature not supported by KVM on this host"); + return -ENOTSUP; + } + } else if ((cpu->lbt == ON_OFF_AUTO_AUTO) && kvm_supported) { + env->cpucfg[2] = FIELD_DP32(env->cpucfg[2], CPUCFG2, LBT_ALL, 7); + } + + return 0; +} + +static int kvm_cpu_check_pmu(CPUState *cs, Error **errp) +{ + LoongArchCPU *cpu = LOONGARCH_CPU(cs); + CPULoongArchState *env = cpu_env(cs); + bool kvm_supported; + + kvm_supported = kvm_feature_supported(cs, LOONGARCH_FEATURE_PMU); + if (cpu->pmu == ON_OFF_AUTO_ON) { + if (!kvm_supported) { + error_setg(errp, "'pmu' feature not supported by KVM on the host"); + return -ENOTSUP; + } + } else if (cpu->pmu != ON_OFF_AUTO_AUTO) { + /* disable pmu if ON_OFF_AUTO_OFF is set */ + kvm_supported = false; + } + + if (kvm_supported) { + env->cpucfg[6] = FIELD_DP32(env->cpucfg[6], CPUCFG6, PMP, 1); + env->cpucfg[6] = FIELD_DP32(env->cpucfg[6], CPUCFG6, PMNUM, 3); + env->cpucfg[6] = FIELD_DP32(env->cpucfg[6], CPUCFG6, PMBITS, 63); + env->cpucfg[6] = FIELD_DP32(env->cpucfg[6], CPUCFG6, UPM, 1); + } + return 0; +} + int kvm_arch_init_vcpu(CPUState *cs) { uint64_t val; + int ret; + Error *local_err = NULL; + ret = 0; qemu_add_vm_change_state_handler(kvm_loongarch_vm_stage_change, cs); if (!kvm_get_one_reg(cs, KVM_REG_LOONGARCH_DEBUG_INST, &val)) { brk_insn = val; } - return 0; + ret = kvm_cpu_check_lbt(cs, &local_err); + if (ret < 0) { + error_report_err(local_err); + } + + ret = kvm_cpu_check_pmu(cs, &local_err); + if (ret < 0) { + error_report_err(local_err); + } + + return ret; } int kvm_arch_destroy_vcpu(CPUState *cs) diff --git a/target/loongarch/loongarch-qmp-cmds.c b/target/loongarch/loongarch-qmp-cmds.c index 8721a5eb13..782fd511fd 100644 --- a/target/loongarch/loongarch-qmp-cmds.c +++ b/target/loongarch/loongarch-qmp-cmds.c @@ -40,7 +40,7 @@ CpuDefinitionInfoList *qmp_query_cpu_definitions(Error **errp) } static const char *cpu_model_advertised_features[] = { - "lsx", "lasx", NULL + "lsx", "lasx", "lbt", "pmu", NULL }; CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type, diff --git a/target/loongarch/machine.c b/target/loongarch/machine.c index 08a7fa5370..efb20e2fbe 100644 --- a/target/loongarch/machine.c +++ b/target/loongarch/machine.c @@ -110,6 +110,29 @@ static const VMStateDescription vmstate_lasx = { }, }; +static bool lbt_needed(void *opaque) +{ + LoongArchCPU *cpu = opaque; + + return !!FIELD_EX64(cpu->env.cpucfg[2], CPUCFG2, LBT_ALL); +} + +static const VMStateDescription vmstate_lbt = { + .name = "cpu/lbt", + .version_id = 0, + .minimum_version_id = 0, + .needed = lbt_needed, + .fields = (const VMStateField[]) { + VMSTATE_UINT64(env.lbt.scr0, LoongArchCPU), + VMSTATE_UINT64(env.lbt.scr1, LoongArchCPU), + VMSTATE_UINT64(env.lbt.scr2, LoongArchCPU), + VMSTATE_UINT64(env.lbt.scr3, LoongArchCPU), + VMSTATE_UINT32(env.lbt.eflags, LoongArchCPU), + VMSTATE_UINT32(env.lbt.ftop, LoongArchCPU), + VMSTATE_END_OF_LIST() + }, +}; + #if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) static bool tlb_needed(void *opaque) { @@ -145,8 +168,8 @@ static const VMStateDescription vmstate_tlb = { /* LoongArch CPU state */ const VMStateDescription vmstate_loongarch_cpu = { .name = "cpu", - .version_id = 2, - .minimum_version_id = 2, + .version_id = 3, + .minimum_version_id = 3, .fields = (const VMStateField[]) { VMSTATE_UINTTL_ARRAY(env.gpr, LoongArchCPU, 32), VMSTATE_UINTTL(env.pc, LoongArchCPU), @@ -209,6 +232,8 @@ const VMStateDescription vmstate_loongarch_cpu = { VMSTATE_UINT64(env.CSR_DSAVE, LoongArchCPU), VMSTATE_UINT64(kvm_state_counter, LoongArchCPU), + /* PV steal time */ + VMSTATE_UINT64(env.stealtime.guest_addr, LoongArchCPU), VMSTATE_END_OF_LIST() }, @@ -219,6 +244,7 @@ const VMStateDescription vmstate_loongarch_cpu = { #if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) &vmstate_tlb, #endif + &vmstate_lbt, NULL } }; diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c index 95e45b5029..e6a2803e71 100644 --- a/tests/qtest/migration-test.c +++ b/tests/qtest/migration-test.c @@ -2791,6 +2791,8 @@ static void test_migrate_auto_converge(void) * so we need to decrease a bandwidth. */ const int64_t init_pct = 5, inc_pct = 25, max_pct = 95; + uint64_t prev_dirty_sync_cnt, dirty_sync_cnt; + int max_try_count, hit = 0; if (test_migrate_start(&from, &to, uri, &args)) { return; @@ -2827,6 +2829,36 @@ static void test_migrate_auto_converge(void) } while (true); /* The first percentage of throttling should be at least init_pct */ g_assert_cmpint(percentage, >=, init_pct); + + /* + * End the loop when the dirty sync count greater than 1. + */ + while ((dirty_sync_cnt = get_migration_pass(from)) < 2) { + usleep(1000 * 1000); + } + + prev_dirty_sync_cnt = dirty_sync_cnt; + + /* + * The RAMBlock dirty sync count must changes in 5 seconds, here we set + * the timeout to 10 seconds to ensure it changes. + * + * Note that migrate_ensure_non_converge set the max-bandwidth to 3MB/s, + * while the qtest mem is >= 100MB, one iteration takes at least 33s (100/3) + * to complete; this ensures that the RAMBlock dirty sync occurs. + */ + max_try_count = 10; + while (--max_try_count) { + dirty_sync_cnt = get_migration_pass(from); + if (dirty_sync_cnt != prev_dirty_sync_cnt) { + hit = 1; + break; + } + prev_dirty_sync_cnt = dirty_sync_cnt; + sleep(1); + } + g_assert_cmpint(hit, ==, 1); + /* Now, when we tested that throttling works, let it converge */ migrate_ensure_converge(from); |