aboutsummaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/block/block-global-state.h19
-rw-r--r--include/block/block-io.h2
-rw-r--r--include/block/block_int-common.h32
-rw-r--r--include/block/blockjob.h2
-rw-r--r--include/hw/arm/npcm8xx.h5
-rw-r--r--include/hw/block/flash.h18
-rw-r--r--include/hw/boards.h9
-rw-r--r--include/hw/i386/pc.h7
-rw-r--r--include/hw/i386/tdvf.h45
-rw-r--r--include/hw/i386/x86.h5
-rw-r--r--include/hw/loader.h2
-rw-r--r--include/hw/nvram/fw_cfg.h10
-rw-r--r--include/hw/pci/pci.h316
-rw-r--r--include/hw/pci/pci_device.h1
-rw-r--r--include/hw/pci/pcie.h13
-rw-r--r--include/hw/pci/pcie_regs.h8
-rw-r--r--include/hw/s390x/cpu-topology.h2
-rw-r--r--include/hw/vfio/vfio-container-base.h83
-rw-r--r--include/hw/vfio/vfio-cpr.h18
-rw-r--r--include/hw/virtio/vhost-vdpa.h22
-rw-r--r--include/hw/virtio/virtio-pci.h8
-rw-r--r--include/io/channel-socket.h13
-rw-r--r--include/standard-headers/uefi/uefi.h187
-rw-r--r--include/system/host_iommu_device.h15
-rw-r--r--include/system/iommufd.h54
-rw-r--r--include/system/kvm.h1
-rw-r--r--include/system/memory.h20
27 files changed, 829 insertions, 88 deletions
diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
index 9be34b3..84a2a4e 100644
--- a/include/block/block-global-state.h
+++ b/include/block/block-global-state.h
@@ -192,10 +192,10 @@ int bdrv_inactivate_all(void);
int bdrv_flush_all(void);
void bdrv_close_all(void);
-void bdrv_drain_all_begin(void);
+void GRAPH_UNLOCKED bdrv_drain_all_begin(void);
void bdrv_drain_all_begin_nopoll(void);
void bdrv_drain_all_end(void);
-void bdrv_drain_all(void);
+void GRAPH_UNLOCKED bdrv_drain_all(void);
void bdrv_aio_cancel(BlockAIOCB *acb);
@@ -274,11 +274,16 @@ int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag);
int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
-bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx,
- GHashTable *visited, Transaction *tran,
- Error **errp);
-int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx,
- BdrvChild *ignore_child, Error **errp);
+bool GRAPH_RDLOCK
+bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx,
+ GHashTable *visited, Transaction *tran,
+ Error **errp);
+int GRAPH_UNLOCKED
+bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx,
+ BdrvChild *ignore_child, Error **errp);
+int GRAPH_RDLOCK
+bdrv_try_change_aio_context_locked(BlockDriverState *bs, AioContext *ctx,
+ BdrvChild *ignore_child, Error **errp);
int GRAPH_RDLOCK bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz);
int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo);
diff --git a/include/block/block-io.h b/include/block/block-io.h
index b99cc98..4cf83fb 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -431,7 +431,7 @@ bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent,
*
* This function can be recursive.
*/
-void bdrv_drained_begin(BlockDriverState *bs);
+void GRAPH_UNLOCKED bdrv_drained_begin(BlockDriverState *bs);
/**
* bdrv_do_drained_begin_quiesce:
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 2982dd3..925a3e7 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -396,9 +396,23 @@ struct BlockDriver {
int GRAPH_RDLOCK_PTR (*bdrv_probe_geometry)(
BlockDriverState *bs, HDGeometry *geo);
+ /**
+ * Hot add a BDS's child. Used in combination with bdrv_del_child, so the
+ * user can take a child offline when it is broken and take a new child
+ * online.
+ *
+ * All block nodes must be drained.
+ */
void GRAPH_WRLOCK_PTR (*bdrv_add_child)(
BlockDriverState *parent, BlockDriverState *child, Error **errp);
+ /**
+ * Hot remove a BDS's child. Used in combination with bdrv_add_child, so the
+ * user can take a child offline when it is broken and take a new child
+ * online.
+ *
+ * All block nodes must be drained.
+ */
void GRAPH_WRLOCK_PTR (*bdrv_del_child)(
BlockDriverState *parent, BdrvChild *child, Error **errp);
@@ -983,9 +997,21 @@ struct BdrvChildClass {
bool backing_mask_protocol,
Error **errp);
- bool (*change_aio_ctx)(BdrvChild *child, AioContext *ctx,
- GHashTable *visited, Transaction *tran,
- Error **errp);
+ /*
+ * Notifies the parent that the child is trying to change its AioContext.
+ * The parent may in turn change the AioContext of other nodes in the same
+ * transaction. Returns true if the change is possible and the transaction
+ * can be continued. Returns false and sets @errp if not and the transaction
+ * must be aborted.
+ *
+ * @visited will accumulate all visited BdrvChild objects. The caller is
+ * responsible for freeing the list afterwards.
+ *
+ * Must be called with the affected block nodes drained.
+ */
+ bool GRAPH_RDLOCK_PTR (*change_aio_ctx)(BdrvChild *child, AioContext *ctx,
+ GHashTable *visited,
+ Transaction *tran, Error **errp);
/*
* I/O API functions. These functions are thread-safe.
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 7061ab7..990f3e1 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -137,6 +137,8 @@ BlockJob *block_job_get_locked(const char *id);
* Add @bs to the list of BlockDriverState that are involved in
* @job. This means that all operations will be blocked on @bs while
* @job exists.
+ *
+ * All block nodes must be drained.
*/
int GRAPH_WRLOCK
block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
diff --git a/include/hw/arm/npcm8xx.h b/include/hw/arm/npcm8xx.h
index 3436abf..a8377db 100644
--- a/include/hw/arm/npcm8xx.h
+++ b/include/hw/arm/npcm8xx.h
@@ -28,7 +28,8 @@
#include "hw/misc/npcm7xx_mft.h"
#include "hw/misc/npcm7xx_pwm.h"
#include "hw/misc/npcm7xx_rng.h"
-#include "hw/net/npcm7xx_emc.h"
+#include "hw/net/npcm_gmac.h"
+#include "hw/net/npcm_pcs.h"
#include "hw/nvram/npcm7xx_otp.h"
#include "hw/sd/npcm7xx_sdhci.h"
#include "hw/timer/npcm7xx_timer.h"
@@ -99,6 +100,8 @@ struct NPCM8xxState {
EHCISysBusState ehci[2];
OHCISysBusState ohci[2];
NPCM7xxFIUState fiu[3];
+ NPCMGMACState gmac[4];
+ NPCMPCSState pcs;
NPCM7xxSDHCIState mmc;
NPCMPSPIState pspi;
};
diff --git a/include/hw/block/flash.h b/include/hw/block/flash.h
index 5fd67f5..3671f01 100644
--- a/include/hw/block/flash.h
+++ b/include/hw/block/flash.h
@@ -44,24 +44,6 @@ PFlashCFI02 *pflash_cfi02_register(hwaddr base,
uint16_t unlock_addr1,
int be);
-/* nand.c */
-DeviceState *nand_init(BlockBackend *blk, int manf_id, int chip_id);
-void nand_setpins(DeviceState *dev, uint8_t cle, uint8_t ale,
- uint8_t ce, uint8_t wp, uint8_t gnd);
-void nand_getpins(DeviceState *dev, int *rb);
-void nand_setio(DeviceState *dev, uint32_t value);
-uint32_t nand_getio(DeviceState *dev);
-uint32_t nand_getbuswidth(DeviceState *dev);
-
-#define NAND_MFR_TOSHIBA 0x98
-#define NAND_MFR_SAMSUNG 0xec
-#define NAND_MFR_FUJITSU 0x04
-#define NAND_MFR_NATIONAL 0x8f
-#define NAND_MFR_RENESAS 0x07
-#define NAND_MFR_STMICRO 0x20
-#define NAND_MFR_HYNIX 0xad
-#define NAND_MFR_MICRON 0x2c
-
/* m25p80.c */
#define TYPE_M25P80 "m25p80-generic"
diff --git a/include/hw/boards.h b/include/hw/boards.h
index a7b1fcf..f424b2b 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -286,8 +286,7 @@ struct MachineClass {
no_parallel:1,
no_floppy:1,
no_cdrom:1,
- pci_allow_0_address:1,
- legacy_fw_cfg_order:1;
+ pci_allow_0_address:1;
bool auto_create_sdcard;
bool is_default;
const char *default_machine_opts;
@@ -863,10 +862,4 @@ extern const size_t hw_compat_2_7_len;
extern GlobalProperty hw_compat_2_6[];
extern const size_t hw_compat_2_6_len;
-extern GlobalProperty hw_compat_2_5[];
-extern const size_t hw_compat_2_5_len;
-
-extern GlobalProperty hw_compat_2_4[];
-extern const size_t hw_compat_2_4_len;
-
#endif
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 9563674..79b72c5 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -107,7 +107,6 @@ struct PCMachineClass {
/* RAM / address space compat: */
bool gigabyte_align;
bool has_reserved_memory;
- bool broken_reserved_end;
bool enforce_amd_1tb_hole;
bool isa_bios_alias;
@@ -299,12 +298,6 @@ extern const size_t pc_compat_2_7_len;
extern GlobalProperty pc_compat_2_6[];
extern const size_t pc_compat_2_6_len;
-extern GlobalProperty pc_compat_2_5[];
-extern const size_t pc_compat_2_5_len;
-
-extern GlobalProperty pc_compat_2_4[];
-extern const size_t pc_compat_2_4_len;
-
#define DEFINE_PC_MACHINE(suffix, namestr, initfn, optsfn) \
static void pc_machine_##suffix##_class_init(ObjectClass *oc, \
const void *data) \
diff --git a/include/hw/i386/tdvf.h b/include/hw/i386/tdvf.h
new file mode 100644
index 0000000..e75c8d1
--- /dev/null
+++ b/include/hw/i386/tdvf.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2025 Intel Corporation
+ * Author: Isaku Yamahata <isaku.yamahata at gmail.com>
+ * <isaku.yamahata at intel.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef HW_I386_TDVF_H
+#define HW_I386_TDVF_H
+
+#include "qemu/osdep.h"
+
+#define TDVF_SECTION_TYPE_BFV 0
+#define TDVF_SECTION_TYPE_CFV 1
+#define TDVF_SECTION_TYPE_TD_HOB 2
+#define TDVF_SECTION_TYPE_TEMP_MEM 3
+
+#define TDVF_SECTION_ATTRIBUTES_MR_EXTEND (1U << 0)
+#define TDVF_SECTION_ATTRIBUTES_PAGE_AUG (1U << 1)
+
+typedef struct TdxFirmwareEntry {
+ uint32_t data_offset;
+ uint32_t data_len;
+ uint64_t address;
+ uint64_t size;
+ uint32_t type;
+ uint32_t attributes;
+
+ void *mem_ptr;
+} TdxFirmwareEntry;
+
+typedef struct TdxFirmware {
+ void *mem_ptr;
+
+ uint32_t nr_entries;
+ TdxFirmwareEntry *entries;
+} TdxFirmware;
+
+#define for_each_tdx_fw_entry(fw, e) \
+ for (e = (fw)->entries; e != (fw)->entries + (fw)->nr_entries; e++)
+
+int tdvf_parse_metadata(TdxFirmware *fw, void *flash_ptr, int size);
+
+#endif /* HW_I386_TDVF_H */
diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h
index 258b134..fc460b8 100644
--- a/include/hw/i386/x86.h
+++ b/include/hw/i386/x86.h
@@ -27,13 +27,8 @@
#include "qom/object.h"
struct X86MachineClass {
- /*< private >*/
MachineClass parent;
- /*< public >*/
-
- /* TSC rate migration: */
- bool save_tsc_khz;
/* use DMA capable linuxboot option rom */
bool fwcfg_dma_enabled;
/* CPU and apic information: */
diff --git a/include/hw/loader.h b/include/hw/loader.h
index d280dc3..c96b5e1 100644
--- a/include/hw/loader.h
+++ b/include/hw/loader.h
@@ -270,8 +270,6 @@ int rom_add_elf_program(const char *name, GMappedFile *mapped_file, void *data,
AddressSpace *as);
int rom_check_and_register_reset(void);
void rom_set_fw(FWCfgState *f);
-void rom_set_order_override(int order);
-void rom_reset_order_override(void);
/**
* rom_transaction_begin:
diff --git a/include/hw/nvram/fw_cfg.h b/include/hw/nvram/fw_cfg.h
index 47578cc..d41b932 100644
--- a/include/hw/nvram/fw_cfg.h
+++ b/include/hw/nvram/fw_cfg.h
@@ -42,14 +42,6 @@ struct FWCfgDataGeneratorClass {
typedef struct fw_cfg_file FWCfgFile;
-#define FW_CFG_ORDER_OVERRIDE_VGA 70
-#define FW_CFG_ORDER_OVERRIDE_NIC 80
-#define FW_CFG_ORDER_OVERRIDE_USER 100
-#define FW_CFG_ORDER_OVERRIDE_DEVICE 110
-
-void fw_cfg_set_order_override(FWCfgState *fw_cfg, int order);
-void fw_cfg_reset_order_override(FWCfgState *fw_cfg);
-
typedef struct FWCfgFiles {
uint32_t count;
FWCfgFile f[];
@@ -75,8 +67,6 @@ struct FWCfgState {
uint32_t cur_offset;
Notifier machine_ready;
- int fw_cfg_order_override;
-
bool dma_enabled;
dma_addr_t dma_addr;
AddressSpace *dma_as;
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index c2fe6ca..35d59d7 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -375,6 +375,28 @@ void pci_bus_get_w64_range(PCIBus *bus, Range *range);
void pci_device_deassert_intx(PCIDevice *dev);
+/* Page Request Interface */
+typedef enum {
+ IOMMU_PRI_RESP_SUCCESS,
+ IOMMU_PRI_RESP_INVALID_REQUEST,
+ IOMMU_PRI_RESP_FAILURE,
+} IOMMUPRIResponseCode;
+
+typedef struct IOMMUPRIResponse {
+ IOMMUPRIResponseCode response_code;
+ uint16_t prgi;
+} IOMMUPRIResponse;
+
+struct IOMMUPRINotifier;
+
+typedef void (*IOMMUPRINotify)(struct IOMMUPRINotifier *notifier,
+ IOMMUPRIResponse *response);
+
+typedef struct IOMMUPRINotifier {
+ IOMMUPRINotify notify;
+} IOMMUPRINotifier;
+
+#define PCI_PRI_PRGI_MASK 0x1ffU
/**
* struct PCIIOMMUOps: callbacks structure for specific IOMMU handlers
@@ -429,6 +451,179 @@ typedef struct PCIIOMMUOps {
* @devfn: device and function number of the PCI device.
*/
void (*unset_iommu_device)(PCIBus *bus, void *opaque, int devfn);
+ /**
+ * @get_iotlb_info: get properties required to initialize a device IOTLB.
+ *
+ * Callback required if devices are allowed to cache translations.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @addr_width: the address width of the IOMMU (output parameter).
+ *
+ * @min_page_size: the page size of the IOMMU (output parameter).
+ */
+ void (*get_iotlb_info)(void *opaque, uint8_t *addr_width,
+ uint32_t *min_page_size);
+ /**
+ * @init_iotlb_notifier: initialize an IOMMU notifier.
+ *
+ * Optional callback.
+ *
+ * @bus: the #PCIBus of the PCI device.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @devfn: device and function number of the PCI device.
+ *
+ * @n: the notifier to be initialized.
+ *
+ * @fn: the callback to be installed.
+ *
+ * @user_opaque: a user pointer that can be used to track a state.
+ */
+ void (*init_iotlb_notifier)(PCIBus *bus, void *opaque, int devfn,
+ IOMMUNotifier *n, IOMMUNotify fn,
+ void *user_opaque);
+ /**
+ * @register_iotlb_notifier: setup an IOTLB invalidation notifier.
+ *
+ * Callback required if devices are allowed to cache translations.
+ *
+ * @bus: the #PCIBus of the PCI device.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @devfn: device and function number of the PCI device.
+ *
+ * @pasid: the pasid of the address space to watch.
+ *
+ * @n: the notifier to register.
+ */
+ void (*register_iotlb_notifier)(PCIBus *bus, void *opaque, int devfn,
+ uint32_t pasid, IOMMUNotifier *n);
+ /**
+ * @unregister_iotlb_notifier: remove an IOTLB invalidation notifier.
+ *
+ * Callback required if devices are allowed to cache translations.
+ *
+ * @bus: the #PCIBus of the PCI device.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @devfn: device and function number of the PCI device.
+ *
+ * @pasid: the pasid of the address space to stop watching.
+ *
+ * @n: the notifier to unregister.
+ */
+ void (*unregister_iotlb_notifier)(PCIBus *bus, void *opaque, int devfn,
+ uint32_t pasid, IOMMUNotifier *n);
+ /**
+ * @ats_request_translation: issue an ATS request.
+ *
+ * Callback required if devices are allowed to use the address
+ * translation service.
+ *
+ * @bus: the #PCIBus of the PCI device.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @devfn: device and function number of the PCI device.
+ *
+ * @pasid: the pasid of the address space to use for the request.
+ *
+ * @priv_req: privileged mode bit (PASID TLP).
+ *
+ * @exec_req: execute request bit (PASID TLP).
+ *
+ * @addr: start address of the memory range to be translated.
+ *
+ * @length: length of the memory range in bytes.
+ *
+ * @no_write: request a read-only translation (if supported).
+ *
+ * @result: buffer in which the TLB entries will be stored.
+ *
+ * @result_length: result buffer length.
+ *
+ * @err_count: number of untranslated subregions.
+ *
+ * Returns: the number of translations stored in the result buffer, or
+ * -ENOMEM if the buffer is not large enough.
+ */
+ ssize_t (*ats_request_translation)(PCIBus *bus, void *opaque, int devfn,
+ uint32_t pasid, bool priv_req,
+ bool exec_req, hwaddr addr,
+ size_t length, bool no_write,
+ IOMMUTLBEntry *result,
+ size_t result_length,
+ uint32_t *err_count);
+ /**
+ * @pri_register_notifier: setup the PRI completion callback.
+ *
+ * Callback required if devices are allowed to use the page request
+ * interface.
+ *
+ * @bus: the #PCIBus of the PCI device.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @devfn: device and function number of the PCI device.
+ *
+ * @pasid: the pasid of the address space to track.
+ *
+ * @notifier: the notifier to register.
+ */
+ void (*pri_register_notifier)(PCIBus *bus, void *opaque, int devfn,
+ uint32_t pasid, IOMMUPRINotifier *notifier);
+ /**
+ * @pri_unregister_notifier: remove the PRI completion callback.
+ *
+ * Callback required if devices are allowed to use the page request
+ * interface.
+ *
+ * @bus: the #PCIBus of the PCI device.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @devfn: device and function number of the PCI device.
+ *
+ * @pasid: the pasid of the address space to stop tracking.
+ */
+ void (*pri_unregister_notifier)(PCIBus *bus, void *opaque, int devfn,
+ uint32_t pasid);
+ /**
+ * @pri_request_page: issue a PRI request.
+ *
+ * Callback required if devices are allowed to use the page request
+ * interface.
+ *
+ * @bus: the #PCIBus of the PCI device.
+ *
+ * @opaque: the data passed to pci_setup_iommu().
+ *
+ * @devfn: device and function number of the PCI device.
+ *
+ * @pasid: the pasid of the address space to use for the request.
+ *
+ * @priv_req: privileged mode bit (PASID TLP).
+ *
+ * @exec_req: execute request bit (PASID TLP).
+ *
+ * @addr: untranslated address of the requested page.
+ *
+ * @lpig: last page in group.
+ *
+ * @prgi: page request group index.
+ *
+ * @is_read: request read access.
+ *
+ * @is_write: request write access.
+ */
+ int (*pri_request_page)(PCIBus *bus, void *opaque, int devfn,
+ uint32_t pasid, bool priv_req, bool exec_req,
+ hwaddr addr, bool lpig, uint16_t prgi, bool is_read,
+ bool is_write);
} PCIIOMMUOps;
AddressSpace *pci_device_iommu_address_space(PCIDevice *dev);
@@ -437,6 +632,126 @@ bool pci_device_set_iommu_device(PCIDevice *dev, HostIOMMUDevice *hiod,
void pci_device_unset_iommu_device(PCIDevice *dev);
/**
+ * pci_iommu_get_iotlb_info: get properties required to initialize a
+ * device IOTLB.
+ *
+ * Returns 0 on success, or a negative errno otherwise.
+ *
+ * @dev: the device that wants to get the information.
+ * @addr_width: the address width of the IOMMU (output parameter).
+ * @min_page_size: the page size of the IOMMU (output parameter).
+ */
+int pci_iommu_get_iotlb_info(PCIDevice *dev, uint8_t *addr_width,
+ uint32_t *min_page_size);
+
+/**
+ * pci_iommu_init_iotlb_notifier: initialize an IOMMU notifier.
+ *
+ * This function is used by devices before registering an IOTLB notifier.
+ *
+ * @dev: the device.
+ * @n: the notifier to be initialized.
+ * @fn: the callback to be installed.
+ * @opaque: a user pointer that can be used to track a state.
+ */
+int pci_iommu_init_iotlb_notifier(PCIDevice *dev, IOMMUNotifier *n,
+ IOMMUNotify fn, void *opaque);
+
+/**
+ * pci_ats_request_translation: perform an ATS request.
+ *
+ * Returns the number of translations stored in @result in case of success,
+ * a negative error code otherwise.
+ * -ENOMEM is returned when the result buffer is not large enough to store
+ * all the translations.
+ *
+ * @dev: the ATS-capable PCI device.
+ * @pasid: the pasid of the address space in which the translation will be done.
+ * @priv_req: privileged mode bit (PASID TLP).
+ * @exec_req: execute request bit (PASID TLP).
+ * @addr: start address of the memory range to be translated.
+ * @length: length of the memory range in bytes.
+ * @no_write: request a read-only translation (if supported).
+ * @result: buffer in which the TLB entries will be stored.
+ * @result_length: result buffer length.
+ * @err_count: number of untranslated subregions.
+ */
+ssize_t pci_ats_request_translation(PCIDevice *dev, uint32_t pasid,
+ bool priv_req, bool exec_req,
+ hwaddr addr, size_t length,
+ bool no_write, IOMMUTLBEntry *result,
+ size_t result_length,
+ uint32_t *err_count);
+
+/**
+ * pci_pri_request_page: perform a PRI request.
+ *
+ * Returns 0 if the PRI request has been sent to the guest OS,
+ * an error code otherwise.
+ *
+ * @dev: the PRI-capable PCI device.
+ * @pasid: the pasid of the address space in which the translation will be done.
+ * @priv_req: privileged mode bit (PASID TLP).
+ * @exec_req: execute request bit (PASID TLP).
+ * @addr: untranslated address of the requested page.
+ * @lpig: last page in group.
+ * @prgi: page request group index.
+ * @is_read: request read access.
+ * @is_write: request write access.
+ */
+int pci_pri_request_page(PCIDevice *dev, uint32_t pasid, bool priv_req,
+ bool exec_req, hwaddr addr, bool lpig,
+ uint16_t prgi, bool is_read, bool is_write);
+
+/**
+ * pci_pri_register_notifier: register the PRI callback for a given address
+ * space.
+ *
+ * Returns 0 on success, an error code otherwise.
+ *
+ * @dev: the PRI-capable PCI device.
+ * @pasid: the pasid of the address space to track.
+ * @notifier: the notifier to register.
+ */
+int pci_pri_register_notifier(PCIDevice *dev, uint32_t pasid,
+ IOMMUPRINotifier *notifier);
+
+/**
+ * pci_pri_unregister_notifier: remove the PRI callback from a given address
+ * space.
+ *
+ * @dev: the PRI-capable PCI device.
+ * @pasid: the pasid of the address space to stop tracking.
+ */
+void pci_pri_unregister_notifier(PCIDevice *dev, uint32_t pasid);
+
+/**
+ * pci_iommu_register_iotlb_notifier: register a notifier for changes to
+ * IOMMU translation entries in a specific address space.
+ *
+ * Returns 0 on success, or a negative errno otherwise.
+ *
+ * @dev: the device that wants to get notified.
+ * @pasid: the pasid of the address space to track.
+ * @n: the notifier to register.
+ */
+int pci_iommu_register_iotlb_notifier(PCIDevice *dev, uint32_t pasid,
+ IOMMUNotifier *n);
+
+/**
+ * pci_iommu_unregister_iotlb_notifier: unregister a notifier that has been
+ * registerd with pci_iommu_register_iotlb_notifier.
+ *
+ * Returns 0 on success, or a negative errno otherwise.
+ *
+ * @dev: the device that wants to stop notifications.
+ * @pasid: the pasid of the address space to stop tracking.
+ * @n: the notifier to unregister.
+ */
+int pci_iommu_unregister_iotlb_notifier(PCIDevice *dev, uint32_t pasid,
+ IOMMUNotifier *n);
+
+/**
* pci_setup_iommu: Initialize specific IOMMU handlers for a PCIBus
*
* Let PCI host bridges define specific operations.
@@ -668,6 +983,7 @@ void lsi53c8xx_handle_legacy_cmdline(DeviceState *lsi_dev);
qemu_irq pci_allocate_irq(PCIDevice *pci_dev);
void pci_set_irq(PCIDevice *pci_dev, int level);
+int pci_irq_disabled(PCIDevice *d);
static inline void pci_irq_assert(PCIDevice *pci_dev)
{
diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index e41d95b..eee0338 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -90,6 +90,7 @@ struct PCIDevice {
char name[64];
PCIIORegion io_regions[PCI_NUM_REGIONS];
AddressSpace bus_master_as;
+ bool is_master;
MemoryRegion bus_master_container_region;
MemoryRegion bus_master_enable_region;
diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h
index 70a5de0..ff6ce08 100644
--- a/include/hw/pci/pcie.h
+++ b/include/hw/pci/pcie.h
@@ -70,8 +70,10 @@ struct PCIExpressDevice {
uint16_t aer_cap;
PCIEAERLog aer_log;
- /* Offset of ATS capability in config space */
+ /* Offset of ATS, PRI and PASID capabilities in config space */
uint16_t ats_cap;
+ uint16_t pasid_cap;
+ uint16_t pri_cap;
/* ACS */
uint16_t acs_cap;
@@ -150,4 +152,13 @@ void pcie_cap_slot_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
Error **errp);
void pcie_cap_slot_unplug_request_cb(HotplugHandler *hotplug_dev,
DeviceState *dev, Error **errp);
+
+void pcie_pasid_init(PCIDevice *dev, uint16_t offset, uint8_t pasid_width,
+ bool exec_perm, bool priv_mod);
+void pcie_pri_init(PCIDevice *dev, uint16_t offset, uint32_t outstanding_pr_cap,
+ bool prg_response_pasid_req);
+
+bool pcie_pri_enabled(const PCIDevice *dev);
+bool pcie_pasid_enabled(const PCIDevice *dev);
+bool pcie_ats_enabled(const PCIDevice *dev);
#endif /* QEMU_PCIE_H */
diff --git a/include/hw/pci/pcie_regs.h b/include/hw/pci/pcie_regs.h
index 9d3b686..33a2222 100644
--- a/include/hw/pci/pcie_regs.h
+++ b/include/hw/pci/pcie_regs.h
@@ -86,6 +86,14 @@ typedef enum PCIExpLinkWidth {
#define PCI_ARI_VER 1
#define PCI_ARI_SIZEOF 8
+/* PASID */
+#define PCI_PASID_VER 1
+#define PCI_EXT_CAP_PASID_MAX_WIDTH 20
+#define PCI_PASID_CAP_WIDTH_SHIFT 8
+
+/* PRI */
+#define PCI_PRI_VER 1
+
/* AER */
#define PCI_ERR_VER 2
#define PCI_ERR_SIZEOF 0x48
diff --git a/include/hw/s390x/cpu-topology.h b/include/hw/s390x/cpu-topology.h
index 9283c94..d5e9aa4 100644
--- a/include/hw/s390x/cpu-topology.h
+++ b/include/hw/s390x/cpu-topology.h
@@ -13,7 +13,7 @@
#include "qemu/queue.h"
#include "hw/boards.h"
-#include "qapi/qapi-types-machine-target.h"
+#include "qapi/qapi-types-machine-s390x.h"
#define S390_TOPOLOGY_CPU_IFL 0x03
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 3d392b0..9d37f86 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -78,7 +78,7 @@ void vfio_address_space_insert(VFIOAddressSpace *space,
int vfio_container_dma_map(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- void *vaddr, bool readonly);
+ void *vaddr, bool readonly, MemoryRegion *mr);
int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
IOMMUTLBEntry *iotlb, bool unmap_all);
@@ -115,13 +115,57 @@ OBJECT_DECLARE_TYPE(VFIOContainerBase, VFIOIOMMUClass, VFIO_IOMMU)
struct VFIOIOMMUClass {
ObjectClass parent_class;
- /* basic feature */
+ /**
+ * @setup
+ *
+ * Perform basic setup of the container, including configuring IOMMU
+ * capabilities, IOVA ranges, supported page sizes, etc.
+ *
+ * @bcontainer: #VFIOContainerBase
+ * @errp: pointer to Error*, to store an error if it happens.
+ *
+ * Returns true to indicate success and false for error.
+ */
bool (*setup)(VFIOContainerBase *bcontainer, Error **errp);
+
+ /**
+ * @listener_begin
+ *
+ * Called at the beginning of an address space update transaction.
+ * See #MemoryListener.
+ *
+ * @bcontainer: #VFIOContainerBase
+ */
void (*listener_begin)(VFIOContainerBase *bcontainer);
+
+ /**
+ * @listener_commit
+ *
+ * Called at the end of an address space update transaction,
+ * See #MemoryListener.
+ *
+ * @bcontainer: #VFIOContainerBase
+ */
void (*listener_commit)(VFIOContainerBase *bcontainer);
+
+ /**
+ * @dma_map
+ *
+ * Map an address range into the container. Note that the memory region is
+ * referenced within an RCU read lock region across this call.
+ *
+ * @bcontainer: #VFIOContainerBase to use
+ * @iova: start address to map
+ * @size: size of the range to map
+ * @vaddr: process virtual address of mapping
+ * @readonly: true if mapping should be readonly
+ * @mr: the memory region for this mapping
+ *
+ * Returns 0 to indicate success and -errno otherwise.
+ */
int (*dma_map)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
- void *vaddr, bool readonly);
+ void *vaddr, bool readonly, MemoryRegion *mr);
/**
* @dma_unmap
*
@@ -132,12 +176,38 @@ struct VFIOIOMMUClass {
* @size: size of the range to unmap
* @iotlb: The IOMMU TLB mapping entry (or NULL)
* @unmap_all: if set, unmap the entire address space
+ *
+ * Returns 0 to indicate success and -errno otherwise.
*/
int (*dma_unmap)(const VFIOContainerBase *bcontainer,
hwaddr iova, ram_addr_t size,
IOMMUTLBEntry *iotlb, bool unmap_all);
+
+
+ /**
+ * @attach_device
+ *
+ * Associate the given device with a container and do some related
+ * initialization of the device context.
+ *
+ * @name: name of the device
+ * @vbasedev: the device
+ * @as: address space to use
+ * @errp: pointer to Error*, to store an error if it happens.
+ *
+ * Returns true to indicate success and false for error.
+ */
bool (*attach_device)(const char *name, VFIODevice *vbasedev,
AddressSpace *as, Error **errp);
+
+ /*
+ * @detach_device
+ *
+ * Detach the given device from its container and clean up any necessary
+ * state.
+ *
+ * @vbasedev: the device to disassociate
+ */
void (*detach_device)(VFIODevice *vbasedev);
/* migration feature */
@@ -152,7 +222,7 @@ struct VFIOIOMMUClass {
* @start: indicates whether to start or stop dirty pages tracking
* @errp: pointer to Error*, to store an error if it happens.
*
- * Returns zero to indicate success and negative for error
+ * Returns zero to indicate success and negative for error.
*/
int (*set_dirty_page_tracking)(const VFIOContainerBase *bcontainer,
bool start, Error **errp);
@@ -167,7 +237,7 @@ struct VFIOIOMMUClass {
* @size: size of iova range
* @errp: pointer to Error*, to store an error if it happens.
*
- * Returns zero to indicate success and negative for error
+ * Returns zero to indicate success and negative for error.
*/
int (*query_dirty_bitmap)(const VFIOContainerBase *bcontainer,
VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp);
@@ -183,4 +253,7 @@ struct VFIOIOMMUClass {
void (*release)(VFIOContainerBase *bcontainer);
};
+VFIORamDiscardListener *vfio_find_ram_discard_listener(
+ VFIOContainerBase *bcontainer, MemoryRegionSection *section);
+
#endif /* HW_VFIO_VFIO_CONTAINER_BASE_H */
diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h
new file mode 100644
index 0000000..750ea5b
--- /dev/null
+++ b/include/hw/vfio/vfio-cpr.h
@@ -0,0 +1,18 @@
+/*
+ * VFIO CPR
+ *
+ * Copyright (c) 2025 Oracle and/or its affiliates.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef HW_VFIO_VFIO_CPR_H
+#define HW_VFIO_VFIO_CPR_H
+
+struct VFIOContainerBase;
+
+bool vfio_cpr_register_container(struct VFIOContainerBase *bcontainer,
+ Error **errp);
+void vfio_cpr_unregister_container(struct VFIOContainerBase *bcontainer);
+
+#endif /* HW_VFIO_VFIO_CPR_H */
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index 0a9575b..449bf5c 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -43,7 +43,21 @@ typedef struct vhost_vdpa_shared {
struct vhost_vdpa_iova_range iova_range;
QLIST_HEAD(, vdpa_iommu) iommu_list;
- /* IOVA mapping used by the Shadow Virtqueue */
+ /*
+ * IOVA mapping used by the Shadow Virtqueue
+ *
+ * It is shared among all ASID for simplicity, whether CVQ shares ASID with
+ * guest or not:
+ * - Memory listener need access to guest's memory addresses allocated in
+ * the IOVA tree.
+ * - There should be plenty of IOVA address space for both ASID not to
+ * worry about collisions between them. Guest's translations are still
+ * validated with virtio virtqueue_pop so there is no risk for the guest
+ * to access memory that it shouldn't.
+ *
+ * To allocate a iova tree per ASID is doable but it complicates the code
+ * and it is not worth it for the moment.
+ */
VhostIOVATree *iova_tree;
/* Copy of backend features */
@@ -51,6 +65,12 @@ typedef struct vhost_vdpa_shared {
bool iotlb_batch_begin_sent;
+ /*
+ * The memory listener has been registered, so DMA maps have been sent to
+ * the device.
+ */
+ bool listener_registered;
+
/* Vdpa must send shadow addresses as IOTLB key for data queues, not GPA */
bool shadow_data;
diff --git a/include/hw/virtio/virtio-pci.h b/include/hw/virtio/virtio-pci.h
index 1dbc385..eab5394 100644
--- a/include/hw/virtio/virtio-pci.h
+++ b/include/hw/virtio/virtio-pci.h
@@ -32,9 +32,7 @@ DECLARE_OBJ_CHECKERS(VirtioPCIBusState, VirtioPCIBusClass,
enum {
VIRTIO_PCI_FLAG_BUS_MASTER_BUG_MIGRATION_BIT,
VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT,
- VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT,
VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT,
- VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT,
VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT,
VIRTIO_PCI_FLAG_ATS_BIT,
VIRTIO_PCI_FLAG_INIT_DEVERR_BIT,
@@ -54,12 +52,6 @@ enum {
* vcpu thread using ioeventfd for some devices. */
#define VIRTIO_PCI_FLAG_USE_IOEVENTFD (1 << VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT)
-/* virtio version flags */
-#define VIRTIO_PCI_FLAG_DISABLE_PCIE (1 << VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT)
-
-/* migrate extra state */
-#define VIRTIO_PCI_FLAG_MIGRATE_EXTRA (1 << VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT)
-
/* have pio notification for modern device ? */
#define VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY \
(1 << VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT)
diff --git a/include/io/channel-socket.h b/include/io/channel-socket.h
index ab15577..a88cf8b 100644
--- a/include/io/channel-socket.h
+++ b/include/io/channel-socket.h
@@ -261,5 +261,18 @@ QIOChannelSocket *
qio_channel_socket_accept(QIOChannelSocket *ioc,
Error **errp);
+/**
+ * qio_channel_socket_set_send_buffer:
+ * @ioc: the socket channel object
+ * @size: buffer size
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Set the underlying socket send buffer size.
+ *
+ * Retruns: 0 on success, or -1 on error.
+ */
+int qio_channel_socket_set_send_buffer(QIOChannelSocket *ioc,
+ size_t size,
+ Error **errp);
#endif /* QIO_CHANNEL_SOCKET_H */
diff --git a/include/standard-headers/uefi/uefi.h b/include/standard-headers/uefi/uefi.h
new file mode 100644
index 0000000..5256349
--- /dev/null
+++ b/include/standard-headers/uefi/uefi.h
@@ -0,0 +1,187 @@
+/*
+ * Copyright (C) 2025 Intel Corporation
+ *
+ * Author: Isaku Yamahata <isaku.yamahata at gmail.com>
+ * <isaku.yamahata at intel.com>
+ * Xiaoyao Li <xiaoyao.li@intel.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef HW_I386_UEFI_H
+#define HW_I386_UEFI_H
+
+/***************************************************************************/
+/*
+ * basic EFI definitions
+ * supplemented with UEFI Specification Version 2.8 (Errata A)
+ * released February 2020
+ */
+/* UEFI integer is little endian */
+
+typedef struct {
+ uint32_t Data1;
+ uint16_t Data2;
+ uint16_t Data3;
+ uint8_t Data4[8];
+} EFI_GUID;
+
+typedef enum {
+ EfiReservedMemoryType,
+ EfiLoaderCode,
+ EfiLoaderData,
+ EfiBootServicesCode,
+ EfiBootServicesData,
+ EfiRuntimeServicesCode,
+ EfiRuntimeServicesData,
+ EfiConventionalMemory,
+ EfiUnusableMemory,
+ EfiACPIReclaimMemory,
+ EfiACPIMemoryNVS,
+ EfiMemoryMappedIO,
+ EfiMemoryMappedIOPortSpace,
+ EfiPalCode,
+ EfiPersistentMemory,
+ EfiUnacceptedMemoryType,
+ EfiMaxMemoryType
+} EFI_MEMORY_TYPE;
+
+#define EFI_HOB_HANDOFF_TABLE_VERSION 0x0009
+
+#define EFI_HOB_TYPE_HANDOFF 0x0001
+#define EFI_HOB_TYPE_MEMORY_ALLOCATION 0x0002
+#define EFI_HOB_TYPE_RESOURCE_DESCRIPTOR 0x0003
+#define EFI_HOB_TYPE_GUID_EXTENSION 0x0004
+#define EFI_HOB_TYPE_FV 0x0005
+#define EFI_HOB_TYPE_CPU 0x0006
+#define EFI_HOB_TYPE_MEMORY_POOL 0x0007
+#define EFI_HOB_TYPE_FV2 0x0009
+#define EFI_HOB_TYPE_LOAD_PEIM_UNUSED 0x000A
+#define EFI_HOB_TYPE_UEFI_CAPSULE 0x000B
+#define EFI_HOB_TYPE_FV3 0x000C
+#define EFI_HOB_TYPE_UNUSED 0xFFFE
+#define EFI_HOB_TYPE_END_OF_HOB_LIST 0xFFFF
+
+typedef struct {
+ uint16_t HobType;
+ uint16_t HobLength;
+ uint32_t Reserved;
+} EFI_HOB_GENERIC_HEADER;
+
+typedef uint64_t EFI_PHYSICAL_ADDRESS;
+typedef uint32_t EFI_BOOT_MODE;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+ uint32_t Version;
+ EFI_BOOT_MODE BootMode;
+ EFI_PHYSICAL_ADDRESS EfiMemoryTop;
+ EFI_PHYSICAL_ADDRESS EfiMemoryBottom;
+ EFI_PHYSICAL_ADDRESS EfiFreeMemoryTop;
+ EFI_PHYSICAL_ADDRESS EfiFreeMemoryBottom;
+ EFI_PHYSICAL_ADDRESS EfiEndOfHobList;
+} EFI_HOB_HANDOFF_INFO_TABLE;
+
+#define EFI_RESOURCE_SYSTEM_MEMORY 0x00000000
+#define EFI_RESOURCE_MEMORY_MAPPED_IO 0x00000001
+#define EFI_RESOURCE_IO 0x00000002
+#define EFI_RESOURCE_FIRMWARE_DEVICE 0x00000003
+#define EFI_RESOURCE_MEMORY_MAPPED_IO_PORT 0x00000004
+#define EFI_RESOURCE_MEMORY_RESERVED 0x00000005
+#define EFI_RESOURCE_IO_RESERVED 0x00000006
+#define EFI_RESOURCE_MEMORY_UNACCEPTED 0x00000007
+#define EFI_RESOURCE_MAX_MEMORY_TYPE 0x00000008
+
+#define EFI_RESOURCE_ATTRIBUTE_PRESENT 0x00000001
+#define EFI_RESOURCE_ATTRIBUTE_INITIALIZED 0x00000002
+#define EFI_RESOURCE_ATTRIBUTE_TESTED 0x00000004
+#define EFI_RESOURCE_ATTRIBUTE_SINGLE_BIT_ECC 0x00000008
+#define EFI_RESOURCE_ATTRIBUTE_MULTIPLE_BIT_ECC 0x00000010
+#define EFI_RESOURCE_ATTRIBUTE_ECC_RESERVED_1 0x00000020
+#define EFI_RESOURCE_ATTRIBUTE_ECC_RESERVED_2 0x00000040
+#define EFI_RESOURCE_ATTRIBUTE_READ_PROTECTED 0x00000080
+#define EFI_RESOURCE_ATTRIBUTE_WRITE_PROTECTED 0x00000100
+#define EFI_RESOURCE_ATTRIBUTE_EXECUTION_PROTECTED 0x00000200
+#define EFI_RESOURCE_ATTRIBUTE_UNCACHEABLE 0x00000400
+#define EFI_RESOURCE_ATTRIBUTE_WRITE_COMBINEABLE 0x00000800
+#define EFI_RESOURCE_ATTRIBUTE_WRITE_THROUGH_CACHEABLE 0x00001000
+#define EFI_RESOURCE_ATTRIBUTE_WRITE_BACK_CACHEABLE 0x00002000
+#define EFI_RESOURCE_ATTRIBUTE_16_BIT_IO 0x00004000
+#define EFI_RESOURCE_ATTRIBUTE_32_BIT_IO 0x00008000
+#define EFI_RESOURCE_ATTRIBUTE_64_BIT_IO 0x00010000
+#define EFI_RESOURCE_ATTRIBUTE_UNCACHED_EXPORTED 0x00020000
+#define EFI_RESOURCE_ATTRIBUTE_READ_ONLY_PROTECTED 0x00040000
+#define EFI_RESOURCE_ATTRIBUTE_READ_ONLY_PROTECTABLE 0x00080000
+#define EFI_RESOURCE_ATTRIBUTE_READ_PROTECTABLE 0x00100000
+#define EFI_RESOURCE_ATTRIBUTE_WRITE_PROTECTABLE 0x00200000
+#define EFI_RESOURCE_ATTRIBUTE_EXECUTION_PROTECTABLE 0x00400000
+#define EFI_RESOURCE_ATTRIBUTE_PERSISTENT 0x00800000
+#define EFI_RESOURCE_ATTRIBUTE_PERSISTABLE 0x01000000
+#define EFI_RESOURCE_ATTRIBUTE_MORE_RELIABLE 0x02000000
+
+typedef uint32_t EFI_RESOURCE_TYPE;
+typedef uint32_t EFI_RESOURCE_ATTRIBUTE_TYPE;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+ EFI_GUID Owner;
+ EFI_RESOURCE_TYPE ResourceType;
+ EFI_RESOURCE_ATTRIBUTE_TYPE ResourceAttribute;
+ EFI_PHYSICAL_ADDRESS PhysicalStart;
+ uint64_t ResourceLength;
+} EFI_HOB_RESOURCE_DESCRIPTOR;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+ EFI_GUID Name;
+
+ /* guid specific data follows */
+} EFI_HOB_GUID_TYPE;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+ EFI_PHYSICAL_ADDRESS BaseAddress;
+ uint64_t Length;
+} EFI_HOB_FIRMWARE_VOLUME;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+ EFI_PHYSICAL_ADDRESS BaseAddress;
+ uint64_t Length;
+ EFI_GUID FvName;
+ EFI_GUID FileName;
+} EFI_HOB_FIRMWARE_VOLUME2;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+ EFI_PHYSICAL_ADDRESS BaseAddress;
+ uint64_t Length;
+ uint32_t AuthenticationStatus;
+ bool ExtractedFv;
+ EFI_GUID FvName;
+ EFI_GUID FileName;
+} EFI_HOB_FIRMWARE_VOLUME3;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+ uint8_t SizeOfMemorySpace;
+ uint8_t SizeOfIoSpace;
+ uint8_t Reserved[6];
+} EFI_HOB_CPU;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+} EFI_HOB_MEMORY_POOL;
+
+typedef struct {
+ EFI_HOB_GENERIC_HEADER Header;
+
+ EFI_PHYSICAL_ADDRESS BaseAddress;
+ uint64_t Length;
+} EFI_HOB_UEFI_CAPSULE;
+
+#define EFI_HOB_OWNER_ZERO \
+ ((EFI_GUID){ 0x00000000, 0x0000, 0x0000, \
+ { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 } })
+
+#endif
diff --git a/include/system/host_iommu_device.h b/include/system/host_iommu_device.h
index 809cced..ab849a4 100644
--- a/include/system/host_iommu_device.h
+++ b/include/system/host_iommu_device.h
@@ -14,6 +14,13 @@
#include "qom/object.h"
#include "qapi/error.h"
+#ifdef CONFIG_LINUX
+#include "linux/iommufd.h"
+
+typedef union VendorCaps {
+ struct iommu_hw_info_vtd vtd;
+ struct iommu_hw_info_arm_smmuv3 smmuv3;
+} VendorCaps;
/**
* struct HostIOMMUDeviceCaps - Define host IOMMU device capabilities.
@@ -22,11 +29,17 @@
*
* @hw_caps: host platform IOMMU capabilities (e.g. on IOMMUFD this represents
* the @out_capabilities value returned from IOMMU_GET_HW_INFO ioctl)
+ *
+ * @vendor_caps: host platform IOMMU vendor specific capabilities (e.g. on
+ * IOMMUFD this represents a user-space buffer filled by kernel
+ * with host IOMMU @type specific hardware information data)
*/
typedef struct HostIOMMUDeviceCaps {
uint32_t type;
uint64_t hw_caps;
+ VendorCaps vendor_caps;
} HostIOMMUDeviceCaps;
+#endif
#define TYPE_HOST_IOMMU_DEVICE "host-iommu-device"
OBJECT_DECLARE_TYPE(HostIOMMUDevice, HostIOMMUDeviceClass, HOST_IOMMU_DEVICE)
@@ -38,7 +51,9 @@ struct HostIOMMUDevice {
void *agent; /* pointer to agent device, ie. VFIO or VDPA device */
PCIBus *aliased_bus;
int aliased_devfn;
+#ifdef CONFIG_LINUX
HostIOMMUDeviceCaps caps;
+#endif
};
/**
diff --git a/include/system/iommufd.h b/include/system/iommufd.h
index cbab75b..283861b 100644
--- a/include/system/iommufd.h
+++ b/include/system/iommufd.h
@@ -61,6 +61,60 @@ bool iommufd_backend_get_dirty_bitmap(IOMMUFDBackend *be, uint32_t hwpt_id,
uint64_t iova, ram_addr_t size,
uint64_t page_size, uint64_t *data,
Error **errp);
+bool iommufd_backend_invalidate_cache(IOMMUFDBackend *be, uint32_t id,
+ uint32_t data_type, uint32_t entry_len,
+ uint32_t *entry_num, void *data,
+ Error **errp);
#define TYPE_HOST_IOMMU_DEVICE_IOMMUFD TYPE_HOST_IOMMU_DEVICE "-iommufd"
+OBJECT_DECLARE_TYPE(HostIOMMUDeviceIOMMUFD, HostIOMMUDeviceIOMMUFDClass,
+ HOST_IOMMU_DEVICE_IOMMUFD)
+
+/* Overload of the host IOMMU device for the iommufd backend */
+struct HostIOMMUDeviceIOMMUFD {
+ HostIOMMUDevice parent_obj;
+
+ IOMMUFDBackend *iommufd;
+ uint32_t devid;
+ uint32_t hwpt_id;
+};
+
+struct HostIOMMUDeviceIOMMUFDClass {
+ HostIOMMUDeviceClass parent_class;
+
+ /**
+ * @attach_hwpt: attach host IOMMU device to IOMMUFD hardware page table.
+ * VFIO and VDPA device can have different implementation.
+ *
+ * Mandatory callback.
+ *
+ * @idev: host IOMMU device backed by IOMMUFD backend.
+ *
+ * @hwpt_id: ID of IOMMUFD hardware page table.
+ *
+ * @errp: pass an Error out when attachment fails.
+ *
+ * Returns: true on success, false on failure.
+ */
+ bool (*attach_hwpt)(HostIOMMUDeviceIOMMUFD *idev, uint32_t hwpt_id,
+ Error **errp);
+ /**
+ * @detach_hwpt: detach host IOMMU device from IOMMUFD hardware page table.
+ * VFIO and VDPA device can have different implementation.
+ *
+ * Mandatory callback.
+ *
+ * @idev: host IOMMU device backed by IOMMUFD backend.
+ *
+ * @errp: pass an Error out when attachment fails.
+ *
+ * Returns: true on success, false on failure.
+ */
+ bool (*detach_hwpt)(HostIOMMUDeviceIOMMUFD *idev, Error **errp);
+};
+
+bool host_iommu_device_iommufd_attach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+ uint32_t hwpt_id, Error **errp);
+bool host_iommu_device_iommufd_detach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+ Error **errp);
#endif
diff --git a/include/system/kvm.h b/include/system/kvm.h
index b690dda..62ec131 100644
--- a/include/system/kvm.h
+++ b/include/system/kvm.h
@@ -376,6 +376,7 @@ int kvm_arch_get_default_type(MachineState *ms);
int kvm_arch_init(MachineState *ms, KVMState *s);
+int kvm_arch_pre_create_vcpu(CPUState *cpu, Error **errp);
int kvm_arch_init_vcpu(CPUState *cpu);
int kvm_arch_destroy_vcpu(CPUState *cpu);
diff --git a/include/system/memory.h b/include/system/memory.h
index fbbf4cf..0848690 100644
--- a/include/system/memory.h
+++ b/include/system/memory.h
@@ -183,6 +183,7 @@ struct IOMMUNotifier {
hwaddr start;
hwaddr end;
int iommu_idx;
+ void *opaque;
QLIST_ENTRY(IOMMUNotifier) node;
};
typedef struct IOMMUNotifier IOMMUNotifier;
@@ -738,21 +739,20 @@ void ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
RamDiscardListener *rdl);
/**
- * memory_get_xlat_addr: Extract addresses from a TLB entry
+ * memory_translate_iotlb: Extract addresses from a TLB entry.
+ * Called with rcu_read_lock held.
*
* @iotlb: pointer to an #IOMMUTLBEntry
- * @vaddr: virtual address
- * @ram_addr: RAM address
- * @read_only: indicates if writes are allowed
- * @mr_has_discard_manager: indicates memory is controlled by a
- * RamDiscardManager
+ * @xlat_p: return the offset of the entry from the start of the returned
+ * MemoryRegion.
* @errp: pointer to Error*, to store an error if it happens.
*
- * Return: true on success, else false setting @errp with error.
+ * Return: On success, return the MemoryRegion containing the @iotlb translated
+ * addr. The MemoryRegion must not be accessed after rcu_read_unlock.
+ * On failure, return NULL, setting @errp with error.
*/
-bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
- ram_addr_t *ram_addr, bool *read_only,
- bool *mr_has_discard_manager, Error **errp);
+MemoryRegion *memory_translate_iotlb(IOMMUTLBEntry *iotlb, hwaddr *xlat_p,
+ Error **errp);
typedef struct CoalescedMemoryRange CoalescedMemoryRange;
typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd;