aboutsummaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/block/aio.h24
-rw-r--r--include/block/block.h39
-rw-r--r--include/block/block_int.h29
-rw-r--r--include/block/blockjob.h7
-rw-r--r--include/glib-compat.h11
-rw-r--r--include/hw/i386/pc.h1
-rw-r--r--include/hw/nvram/chrp_nvram.h54
-rw-r--r--include/hw/nvram/sun_nvram.h (renamed from include/hw/nvram/openbios_firmware_abi.h)47
-rw-r--r--include/hw/ppc/pnv.h129
-rw-r--r--include/hw/ppc/pnv_core.h50
-rw-r--r--include/hw/ppc/pnv_lpc.h67
-rw-r--r--include/hw/ppc/pnv_xscom.h78
-rw-r--r--include/hw/ppc/spapr.h27
-rw-r--r--include/hw/ppc/spapr_ovec.h67
-rw-r--r--include/hw/ppc/spapr_vio.h6
-rw-r--r--include/hw/ppc/xics.h11
-rw-r--r--include/hw/xen/xen_backend.h72
-rw-r--r--include/hw/xen/xen_pvdev.h78
-rw-r--r--include/io/channel.h29
-rw-r--r--include/migration/colo.h38
-rw-r--r--include/migration/failover.h26
-rw-r--r--include/migration/migration.h8
-rw-r--r--include/monitor/monitor.h2
-rw-r--r--include/qemu/rfifolock.h54
-rw-r--r--include/qemu/thread-posix.h6
-rw-r--r--include/qemu/thread-win32.h10
-rw-r--r--include/qemu/thread.h3
-rw-r--r--include/sysemu/block-backend.h1
-rw-r--r--include/sysemu/dma.h6
29 files changed, 777 insertions, 203 deletions
diff --git a/include/block/aio.h b/include/block/aio.h
index b9fe2cb37e..c7ae27c91c 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -18,7 +18,6 @@
#include "qemu/queue.h"
#include "qemu/event_notifier.h"
#include "qemu/thread.h"
-#include "qemu/rfifolock.h"
#include "qemu/timer.h"
typedef struct BlockAIOCB BlockAIOCB;
@@ -54,7 +53,7 @@ struct AioContext {
GSource source;
/* Protects all fields from multi-threaded access */
- RFifoLock lock;
+ QemuRecMutex lock;
/* The list of registered AIO handlers */
QLIST_HEAD(, AioHandler) aio_handlers;
@@ -116,9 +115,6 @@ struct AioContext {
bool notified;
EventNotifier notifier;
- /* Scheduling this BH forces the event loop it iterate */
- QEMUBH *notify_dummy_bh;
-
/* Thread pool for performing work and receiving completion callbacks */
struct ThreadPool *thread_pool;
@@ -453,6 +449,24 @@ static inline bool aio_node_check(AioContext *ctx, bool is_external)
}
/**
+ * Return the AioContext whose event loop runs in the current thread.
+ *
+ * If called from an IOThread this will be the IOThread's AioContext. If
+ * called from another thread it will be the main loop AioContext.
+ */
+AioContext *qemu_get_current_aio_context(void);
+
+/**
+ * @ctx: the aio context
+ *
+ * Return whether we are running in the I/O thread that manages @ctx.
+ */
+static inline bool aio_context_in_iothread(AioContext *ctx)
+{
+ return ctx == qemu_get_current_aio_context();
+}
+
+/**
* aio_context_setup:
* @ctx: the aio context
*
diff --git a/include/block/block.h b/include/block/block.h
index 107c603605..b7dc7d54ae 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -218,7 +218,7 @@ BlockDriverState *bdrv_open(const char *filename, const char *reference,
BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
BlockDriverState *bs,
QDict *options, int flags);
-int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
+int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **errp);
int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp);
int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
BlockReopenQueue *queue, Error **errp);
@@ -314,17 +314,11 @@ BlockAIOCB *bdrv_aio_writev(BdrvChild *child, int64_t sector_num,
BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque);
-BlockAIOCB *bdrv_aio_pdiscard(BlockDriverState *bs,
- int64_t offset, int count,
- BlockCompletionFunc *cb, void *opaque);
void bdrv_aio_cancel(BlockAIOCB *acb);
void bdrv_aio_cancel_async(BlockAIOCB *acb);
/* sg packet commands */
-int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf);
-BlockAIOCB *bdrv_aio_ioctl(BlockDriverState *bs,
- unsigned long int req, void *buf,
- BlockCompletionFunc *cb, void *opaque);
+int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf);
/* Invalidate any cached metadata used by image formats */
void bdrv_invalidate_cache(BlockDriverState *bs, Error **errp);
@@ -340,6 +334,35 @@ void bdrv_drain(BlockDriverState *bs);
void coroutine_fn bdrv_co_drain(BlockDriverState *bs);
void bdrv_drain_all(void);
+#define BDRV_POLL_WHILE(bs, cond) ({ \
+ bool waited_ = false; \
+ BlockDriverState *bs_ = (bs); \
+ AioContext *ctx_ = bdrv_get_aio_context(bs_); \
+ if (aio_context_in_iothread(ctx_)) { \
+ while ((cond)) { \
+ aio_poll(ctx_, true); \
+ waited_ = true; \
+ } \
+ } else { \
+ assert(qemu_get_current_aio_context() == \
+ qemu_get_aio_context()); \
+ /* Ask bdrv_dec_in_flight to wake up the main \
+ * QEMU AioContext. Extra I/O threads never take \
+ * other I/O threads' AioContexts (see for example \
+ * block_job_defer_to_main_loop for how to do it). \
+ */ \
+ assert(!bs_->wakeup); \
+ bs_->wakeup = true; \
+ while ((cond)) { \
+ aio_context_release(ctx_); \
+ aio_poll(qemu_get_aio_context(), true); \
+ aio_context_acquire(ctx_); \
+ waited_ = true; \
+ } \
+ bs_->wakeup = false; \
+ } \
+ waited_; })
+
int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int count);
int bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset, int count);
int bdrv_has_zero_init_1(BlockDriverState *bs);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 3e79228eb0..e7ff58419c 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -62,8 +62,6 @@
enum BdrvTrackedRequestType {
BDRV_TRACKED_READ,
BDRV_TRACKED_WRITE,
- BDRV_TRACKED_FLUSH,
- BDRV_TRACKED_IOCTL,
BDRV_TRACKED_DISCARD,
};
@@ -244,6 +242,8 @@ struct BlockDriver {
BlockAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
unsigned long int req, void *buf,
BlockCompletionFunc *cb, void *opaque);
+ int coroutine_fn (*bdrv_co_ioctl)(BlockDriverState *bs,
+ unsigned long int req, void *buf);
/* List of options for creating images, terminated by name == NULL */
QemuOptsList *create_opts;
@@ -443,7 +443,7 @@ struct BlockDriverState {
note this is a reference count */
CoQueue flush_queue; /* Serializing flush queue */
- BdrvTrackedRequest *active_flush_req; /* Flush request in flight */
+ bool active_flush_req; /* Flush request in flight? */
unsigned int write_gen; /* Current data generation */
unsigned int flushed_gen; /* Flushed write generation */
@@ -471,9 +471,12 @@ struct BlockDriverState {
/* Callback before write request is processed */
NotifierWithReturnList before_write_notifiers;
- /* number of in-flight serialising requests */
+ /* number of in-flight requests; overall and serialising */
+ unsigned int in_flight;
unsigned int serialising_in_flight;
+ bool wakeup;
+
/* Offset after the highest byte written to */
uint64_t wr_highest_offset;
@@ -632,6 +635,21 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
void (*aio_context_detached)(void *),
void *opaque);
+/**
+ * bdrv_wakeup:
+ * @bs: The BlockDriverState for which an I/O operation has been completed.
+ *
+ * Wake up the main thread if it is waiting on BDRV_POLL_WHILE. During
+ * synchronous I/O on a BlockDriverState that is attached to another
+ * I/O thread, the main thread lets the I/O thread's event loop run,
+ * waiting for the I/O operation to complete. A bdrv_wakeup will wake
+ * up the main thread if necessary.
+ *
+ * Manual calls to bdrv_wakeup are rarely necessary, because
+ * bdrv_dec_in_flight already calls it.
+ */
+void bdrv_wakeup(BlockDriverState *bs);
+
#ifdef _WIN32
int is_windows_drive(const char *filename);
#endif
@@ -785,6 +803,9 @@ bool bdrv_requests_pending(BlockDriverState *bs);
void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out);
void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in);
+void bdrv_inc_in_flight(BlockDriverState *bs);
+void bdrv_dec_in_flight(BlockDriverState *bs);
+
void blockdev_close_all_bdrv_states(void);
#endif /* BLOCK_INT_H */
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 4ddb4ae2e1..2bb39f4d29 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -92,6 +92,13 @@ typedef struct BlockJobDriver {
* besides job->blk to the new AioContext.
*/
void (*attached_aio_context)(BlockJob *job, AioContext *new_context);
+
+ /*
+ * If the callback is not NULL, it will be invoked when the job has to be
+ * synchronously cancelled or completed; it should drain BlockDriverStates
+ * as required to ensure progress.
+ */
+ void (*drain)(BlockJob *job);
} BlockJobDriver;
/**
diff --git a/include/glib-compat.h b/include/glib-compat.h
index 8093163bee..3f8370b3e4 100644
--- a/include/glib-compat.h
+++ b/include/glib-compat.h
@@ -304,4 +304,15 @@ static inline void g_slist_free_full(GSList *list, GDestroyNotify free_func)
}
#endif
+#if !GLIB_CHECK_VERSION(2, 26, 0)
+static inline void g_source_set_name(GSource *source, const char *name)
+{
+ /* This is just a debugging aid, so leaving it a no-op */
+}
+static inline void g_source_set_name_by_id(guint tag, const char *name)
+{
+ /* This is just a debugging aid, so leaving it a no-op */
+}
+#endif
+
#endif
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 17fff80c8a..98dc7722c3 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -13,7 +13,6 @@
#include "qemu/bitmap.h"
#include "sysemu/sysemu.h"
#include "hw/pci/pci.h"
-#include "hw/boards.h"
#include "hw/compat.h"
#include "hw/mem/pc-dimm.h"
#include "hw/mem/nvdimm.h"
diff --git a/include/hw/nvram/chrp_nvram.h b/include/hw/nvram/chrp_nvram.h
new file mode 100644
index 0000000000..b4f5b2b104
--- /dev/null
+++ b/include/hw/nvram/chrp_nvram.h
@@ -0,0 +1,54 @@
+/*
+ * Common Hardware Reference Platform NVRAM functions.
+ *
+ * This code is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * 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/>.
+ */
+
+#ifndef CHRP_NVRAM_H
+#define CHRP_NVRAM_H
+
+/* OpenBIOS NVRAM partition */
+typedef struct {
+ uint8_t signature;
+ uint8_t checksum;
+ uint16_t len; /* Big endian, length divided by 16 */
+ char name[12];
+} ChrpNvramPartHdr;
+
+#define CHRP_NVPART_SYSTEM 0x70
+#define CHRP_NVPART_FREE 0x7f
+
+static inline void
+chrp_nvram_finish_partition(ChrpNvramPartHdr *header, uint32_t size)
+{
+ unsigned int i, sum;
+ uint8_t *tmpptr;
+
+ /* Length divided by 16 */
+ header->len = cpu_to_be16(size >> 4);
+
+ /* Checksum */
+ tmpptr = (uint8_t *)header;
+ sum = *tmpptr;
+ for (i = 0; i < 14; i++) {
+ sum += tmpptr[2 + i];
+ sum = (sum + ((sum & 0xff00) >> 8)) & 0xff;
+ }
+ header->checksum = sum & 0xff;
+}
+
+int chrp_nvram_create_system_partition(uint8_t *data, int min_len);
+int chrp_nvram_create_free_partition(uint8_t *data, int len);
+
+#endif
diff --git a/include/hw/nvram/openbios_firmware_abi.h b/include/hw/nvram/sun_nvram.h
index 74cfd56180..68eaa60308 100644
--- a/include/hw/nvram/openbios_firmware_abi.h
+++ b/include/hw/nvram/sun_nvram.h
@@ -1,46 +1,5 @@
-#ifndef OPENBIOS_FIRMWARE_ABI_H
-#define OPENBIOS_FIRMWARE_ABI_H
-
-/* OpenBIOS NVRAM partition */
-struct OpenBIOS_nvpart_v1 {
- uint8_t signature;
- uint8_t checksum;
- uint16_t len; // BE, length divided by 16
- char name[12];
-};
-
-#define OPENBIOS_PART_SYSTEM 0x70
-#define OPENBIOS_PART_FREE 0x7f
-
-static inline void
-OpenBIOS_finish_partition(struct OpenBIOS_nvpart_v1 *header, uint32_t size)
-{
- unsigned int i, sum;
- uint8_t *tmpptr;
-
- // Length divided by 16
- header->len = cpu_to_be16(size >> 4);
-
- // Checksum
- tmpptr = (uint8_t *)header;
- sum = *tmpptr;
- for (i = 0; i < 14; i++) {
- sum += tmpptr[2 + i];
- sum = (sum + ((sum & 0xff00) >> 8)) & 0xff;
- }
- header->checksum = sum & 0xff;
-}
-
-static inline uint32_t
-OpenBIOS_set_var(uint8_t *nvram, uint32_t addr, const char *str)
-{
- uint32_t len;
-
- len = strlen(str) + 1;
- memcpy(&nvram[addr], str, len);
-
- return addr + len;
-}
+#ifndef SUN_NVRAM_H
+#define SUN_NVRAM_H
/* Sun IDPROM structure at the end of NVRAM */
/* from http://www.squirrel.com/squirrel/sun-nvram-hostid.faq.html */
@@ -72,4 +31,4 @@ Sun_init_header(struct Sun_nvram *header, const uint8_t *macaddr, int machine_id
header->checksum = tmp;
}
-#endif /* OPENBIOS_FIRMWARE_ABI_H */
+#endif /* SUN_NVRAM_H */
diff --git a/include/hw/ppc/pnv.h b/include/hw/ppc/pnv.h
new file mode 100644
index 0000000000..02ac1c5f42
--- /dev/null
+++ b/include/hw/ppc/pnv.h
@@ -0,0 +1,129 @@
+/*
+ * QEMU PowerPC PowerNV various definitions
+ *
+ * Copyright (c) 2014-2016 BenH, IBM Corporation.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _PPC_PNV_H
+#define _PPC_PNV_H
+
+#include "hw/boards.h"
+#include "hw/sysbus.h"
+#include "hw/ppc/pnv_xscom.h"
+#include "hw/ppc/pnv_lpc.h"
+
+#define TYPE_PNV_CHIP "powernv-chip"
+#define PNV_CHIP(obj) OBJECT_CHECK(PnvChip, (obj), TYPE_PNV_CHIP)
+#define PNV_CHIP_CLASS(klass) \
+ OBJECT_CLASS_CHECK(PnvChipClass, (klass), TYPE_PNV_CHIP)
+#define PNV_CHIP_GET_CLASS(obj) \
+ OBJECT_GET_CLASS(PnvChipClass, (obj), TYPE_PNV_CHIP)
+
+typedef enum PnvChipType {
+ PNV_CHIP_POWER8E, /* AKA Murano (default) */
+ PNV_CHIP_POWER8, /* AKA Venice */
+ PNV_CHIP_POWER8NVL, /* AKA Naples */
+ PNV_CHIP_POWER9, /* AKA Nimbus */
+} PnvChipType;
+
+typedef struct PnvChip {
+ /*< private >*/
+ SysBusDevice parent_obj;
+
+ /*< public >*/
+ uint32_t chip_id;
+ uint64_t ram_start;
+ uint64_t ram_size;
+
+ uint32_t nr_cores;
+ uint64_t cores_mask;
+ void *cores;
+
+ hwaddr xscom_base;
+ MemoryRegion xscom_mmio;
+ MemoryRegion xscom;
+ AddressSpace xscom_as;
+
+ PnvLpcController lpc;
+} PnvChip;
+
+typedef struct PnvChipClass {
+ /*< private >*/
+ SysBusDeviceClass parent_class;
+
+ /*< public >*/
+ const char *cpu_model;
+ PnvChipType chip_type;
+ uint64_t chip_cfam_id;
+ uint64_t cores_mask;
+
+ hwaddr xscom_base;
+
+ uint32_t (*core_pir)(PnvChip *chip, uint32_t core_id);
+} PnvChipClass;
+
+#define TYPE_PNV_CHIP_POWER8E TYPE_PNV_CHIP "-POWER8E"
+#define PNV_CHIP_POWER8E(obj) \
+ OBJECT_CHECK(PnvChip, (obj), TYPE_PNV_CHIP_POWER8E)
+
+#define TYPE_PNV_CHIP_POWER8 TYPE_PNV_CHIP "-POWER8"
+#define PNV_CHIP_POWER8(obj) \
+ OBJECT_CHECK(PnvChip, (obj), TYPE_PNV_CHIP_POWER8)
+
+#define TYPE_PNV_CHIP_POWER8NVL TYPE_PNV_CHIP "-POWER8NVL"
+#define PNV_CHIP_POWER8NVL(obj) \
+ OBJECT_CHECK(PnvChip, (obj), TYPE_PNV_CHIP_POWER8NVL)
+
+#define TYPE_PNV_CHIP_POWER9 TYPE_PNV_CHIP "-POWER9"
+#define PNV_CHIP_POWER9(obj) \
+ OBJECT_CHECK(PnvChip, (obj), TYPE_PNV_CHIP_POWER9)
+
+/*
+ * This generates a HW chip id depending on an index:
+ *
+ * 0x0, 0x1, 0x10, 0x11
+ *
+ * 4 chips should be the maximum
+ */
+#define PNV_CHIP_HWID(i) ((((i) & 0x3e) << 3) | ((i) & 0x1))
+
+#define TYPE_POWERNV_MACHINE MACHINE_TYPE_NAME("powernv")
+#define POWERNV_MACHINE(obj) \
+ OBJECT_CHECK(PnvMachineState, (obj), TYPE_POWERNV_MACHINE)
+
+typedef struct PnvMachineState {
+ /*< private >*/
+ MachineState parent_obj;
+
+ uint32_t initrd_base;
+ long initrd_size;
+
+ uint32_t num_chips;
+ PnvChip **chips;
+
+ ISABus *isa_bus;
+} PnvMachineState;
+
+#define PNV_FDT_ADDR 0x01000000
+#define PNV_TIMEBASE_FREQ 512000000ULL
+
+/*
+ * POWER8 MMIO base addresses
+ */
+#define PNV_XSCOM_SIZE 0x800000000ull
+#define PNV_XSCOM_BASE(chip) \
+ (chip->xscom_base + ((uint64_t)(chip)->chip_id) * PNV_XSCOM_SIZE)
+
+#endif /* _PPC_PNV_H */
diff --git a/include/hw/ppc/pnv_core.h b/include/hw/ppc/pnv_core.h
new file mode 100644
index 0000000000..2955a41c90
--- /dev/null
+++ b/include/hw/ppc/pnv_core.h
@@ -0,0 +1,50 @@
+/*
+ * QEMU PowerPC PowerNV CPU Core model
+ *
+ * Copyright (c) 2016, IBM Corporation.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public License
+ * as published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _PPC_PNV_CORE_H
+#define _PPC_PNV_CORE_H
+
+#include "hw/cpu/core.h"
+
+#define TYPE_PNV_CORE "powernv-cpu-core"
+#define PNV_CORE(obj) \
+ OBJECT_CHECK(PnvCore, (obj), TYPE_PNV_CORE)
+#define PNV_CORE_CLASS(klass) \
+ OBJECT_CLASS_CHECK(PnvCoreClass, (klass), TYPE_PNV_CORE)
+#define PNV_CORE_GET_CLASS(obj) \
+ OBJECT_GET_CLASS(PnvCoreClass, (obj), TYPE_PNV_CORE)
+
+typedef struct PnvCore {
+ /*< private >*/
+ CPUCore parent_obj;
+
+ /*< public >*/
+ void *threads;
+ uint32_t pir;
+
+ MemoryRegion xscom_regs;
+} PnvCore;
+
+typedef struct PnvCoreClass {
+ DeviceClass parent_class;
+ ObjectClass *cpu_oc;
+} PnvCoreClass;
+
+extern char *pnv_core_typename(const char *model);
+
+#endif /* _PPC_PNV_CORE_H */
diff --git a/include/hw/ppc/pnv_lpc.h b/include/hw/ppc/pnv_lpc.h
new file mode 100644
index 0000000000..38e5506975
--- /dev/null
+++ b/include/hw/ppc/pnv_lpc.h
@@ -0,0 +1,67 @@
+/*
+ * QEMU PowerPC PowerNV LPC controller
+ *
+ * Copyright (c) 2016, IBM Corporation.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _PPC_PNV_LPC_H
+#define _PPC_PNV_LPC_H
+
+#define TYPE_PNV_LPC "pnv-lpc"
+#define PNV_LPC(obj) \
+ OBJECT_CHECK(PnvLpcController, (obj), TYPE_PNV_LPC)
+
+typedef struct PnvLpcController {
+ DeviceState parent;
+
+ uint64_t eccb_stat_reg;
+ uint32_t eccb_data_reg;
+
+ /* OPB bus */
+ MemoryRegion opb_mr;
+ AddressSpace opb_as;
+
+ /* ISA IO and Memory space */
+ MemoryRegion isa_io;
+ MemoryRegion isa_mem;
+
+ /* Windows from OPB to ISA (aliases) */
+ MemoryRegion opb_isa_io;
+ MemoryRegion opb_isa_mem;
+ MemoryRegion opb_isa_fw;
+
+ /* Registers */
+ MemoryRegion lpc_hc_regs;
+ MemoryRegion opb_master_regs;
+
+ /* OPB Master LS registers */
+ uint32_t opb_irq_stat;
+ uint32_t opb_irq_mask;
+ uint32_t opb_irq_pol;
+ uint32_t opb_irq_input;
+
+ /* LPC HC registers */
+ uint32_t lpc_hc_fw_seg_idsel;
+ uint32_t lpc_hc_fw_rd_acc_size;
+ uint32_t lpc_hc_irqser_ctrl;
+ uint32_t lpc_hc_irqmask;
+ uint32_t lpc_hc_irqstat;
+ uint32_t lpc_hc_error_addr;
+
+ /* XSCOM registers */
+ MemoryRegion xscom_regs;
+} PnvLpcController;
+
+#endif /* _PPC_PNV_LPC_H */
diff --git a/include/hw/ppc/pnv_xscom.h b/include/hw/ppc/pnv_xscom.h
new file mode 100644
index 0000000000..c0a2fbb9f6
--- /dev/null
+++ b/include/hw/ppc/pnv_xscom.h
@@ -0,0 +1,78 @@
+/*
+ * QEMU PowerPC PowerNV XSCOM bus definitions
+ *
+ * Copyright (c) 2016, IBM Corporation.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library 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
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _PPC_PNV_XSCOM_H
+#define _PPC_PNV_XSCOM_H
+
+#include "qom/object.h"
+
+typedef struct PnvChip PnvChip;
+
+typedef struct PnvXScomInterface {
+ Object parent;
+} PnvXScomInterface;
+
+#define TYPE_PNV_XSCOM_INTERFACE "pnv-xscom-interface"
+#define PNV_XSCOM_INTERFACE(obj) \
+ OBJECT_CHECK(PnvXScomInterface, (obj), TYPE_PNV_XSCOM_INTERFACE)
+#define PNV_XSCOM_INTERFACE_CLASS(klass) \
+ OBJECT_CLASS_CHECK(PnvXScomInterfaceClass, (klass), \
+ TYPE_PNV_XSCOM_INTERFACE)
+#define PNV_XSCOM_INTERFACE_GET_CLASS(obj) \
+ OBJECT_GET_CLASS(PnvXScomInterfaceClass, (obj), TYPE_PNV_XSCOM_INTERFACE)
+
+typedef struct PnvXScomInterfaceClass {
+ InterfaceClass parent;
+ int (*populate)(PnvXScomInterface *dev, void *fdt, int offset);
+} PnvXScomInterfaceClass;
+
+/*
+ * Layout of the XSCOM PCB addresses of EX core 1
+ *
+ * GPIO 0x1100xxxx
+ * SCOM 0x1101xxxx
+ * OHA 0x1102xxxx
+ * CLOCK CTL 0x1103xxxx
+ * FIR 0x1104xxxx
+ * THERM 0x1105xxxx
+ * <reserved> 0x1106xxxx
+ * ..
+ * 0x110Exxxx
+ * PCB SLAVE 0x110Fxxxx
+ */
+
+#define PNV_XSCOM_EX_BASE 0x10000000
+#define PNV_XSCOM_EX_CORE_BASE(i) (PNV_XSCOM_EX_BASE | (((uint64_t)i) << 24))
+#define PNV_XSCOM_EX_CORE_SIZE 0x100000
+
+#define PNV_XSCOM_LPC_BASE 0xb0020
+#define PNV_XSCOM_LPC_SIZE 0x4
+
+extern void pnv_xscom_realize(PnvChip *chip, Error **errp);
+extern int pnv_xscom_populate(PnvChip *chip, void *fdt, int offset);
+
+extern void pnv_xscom_add_subregion(PnvChip *chip, hwaddr offset,
+ MemoryRegion *mr);
+extern void pnv_xscom_region_init(MemoryRegion *mr,
+ struct Object *owner,
+ const MemoryRegionOps *ops,
+ void *opaque,
+ const char *name,
+ uint64_t size);
+
+#endif /* _PPC_PNV_XSCOM_H */
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index aeaba3edf9..bd5bcf70de 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -6,12 +6,14 @@
#include "hw/ppc/xics.h"
#include "hw/ppc/spapr_drc.h"
#include "hw/mem/pc-dimm.h"
+#include "hw/ppc/spapr_ovec.h"
struct VIOsPAPRBus;
struct sPAPRPHBState;
struct sPAPRNVRAM;
typedef struct sPAPRConfigureConnectorState sPAPRConfigureConnectorState;
typedef struct sPAPREventLogEntry sPAPREventLogEntry;
+typedef struct sPAPREventSource sPAPREventSource;
#define HPTE64_V_HPTE_DIRTY 0x0000000000000040ULL
#define SPAPR_ENTRY_POINT 0x100
@@ -63,17 +65,23 @@ struct sPAPRMachineState {
uint32_t htab_shift;
hwaddr rma_size;
int vrma_adjust;
- hwaddr fdt_addr, rtas_addr;
ssize_t rtas_size;
void *rtas_blob;
- void *fdt_skel;
+ long kernel_size;
+ bool kernel_le;
+ uint32_t initrd_base;
+ long initrd_size;
uint64_t rtc_offset; /* Now used only during incoming migration */
struct PPCTimebase tb;
bool has_graphics;
+ sPAPROptionVector *ov5; /* QEMU-supported option vectors */
+ sPAPROptionVector *ov5_cas; /* negotiated (via CAS) option vectors */
+ bool cas_reboot;
- uint32_t check_exception_irq;
Notifier epow_notifier;
QTAILQ_HEAD(, sPAPREventLogEntry) pending_events;
+ bool use_hotplug_event_source;
+ sPAPREventSource *event_sources;
/* Migration state */
int htab_save_index;
@@ -527,8 +535,8 @@ void spapr_rtas_register(int token, const char *name, spapr_rtas_fn fn);
target_ulong spapr_rtas_call(PowerPCCPU *cpu, sPAPRMachineState *sm,
uint32_t token, uint32_t nargs, target_ulong args,
uint32_t nret, target_ulong rets);
-int spapr_rtas_device_tree_setup(void *fdt, hwaddr rtas_addr,
- hwaddr rtas_size);
+void spapr_dt_rtas_tokens(void *fdt, int rtas);
+void spapr_load_rtas(sPAPRMachineState *spapr, void *fdt, hwaddr addr);
#define SPAPR_TCE_PAGE_SHIFT 12
#define SPAPR_TCE_PAGE_SIZE (1ULL << SPAPR_TCE_PAGE_SHIFT)
@@ -578,10 +586,11 @@ struct sPAPREventLogEntry {
};
void spapr_events_init(sPAPRMachineState *sm);
-void spapr_events_fdt_skel(void *fdt, uint32_t epow_irq);
+void spapr_dt_events(sPAPRMachineState *sm, void *fdt);
int spapr_h_cas_compose_response(sPAPRMachineState *sm,
target_ulong addr, target_ulong size,
- bool cpu_update, bool memory_update);
+ bool cpu_update,
+ sPAPROptionVector *ov5_updates);
sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn);
void spapr_tce_table_enable(sPAPRTCETable *tcet,
uint32_t page_shift, uint64_t bus_offset,
@@ -601,6 +610,10 @@ void spapr_hotplug_req_add_by_count(sPAPRDRConnectorType drc_type,
uint32_t count);
void spapr_hotplug_req_remove_by_count(sPAPRDRConnectorType drc_type,
uint32_t count);
+void spapr_hotplug_req_add_by_count_indexed(sPAPRDRConnectorType drc_type,
+ uint32_t count, uint32_t index);
+void spapr_hotplug_req_remove_by_count_indexed(sPAPRDRConnectorType drc_type,
+ uint32_t count, uint32_t index);
void spapr_cpu_init(sPAPRMachineState *spapr, PowerPCCPU *cpu, Error **errp);
void *spapr_populate_hotplug_cpu_dt(CPUState *cs, int *fdt_offset,
sPAPRMachineState *spapr);
diff --git a/include/hw/ppc/spapr_ovec.h b/include/hw/ppc/spapr_ovec.h
new file mode 100644
index 0000000000..6a06da32e6
--- /dev/null
+++ b/include/hw/ppc/spapr_ovec.h
@@ -0,0 +1,67 @@
+/*
+ * QEMU SPAPR Option/Architecture Vector Definitions
+ *
+ * Each architecture option is organized/documented by the following
+ * in LoPAPR 1.1, Table 244:
+ *
+ * <vector number>: the bit-vector in which the option is located
+ * <vector byte>: the byte offset of the vector entry
+ * <vector bit>: the bit offset within the vector entry
+ *
+ * where each vector entry can be one or more bytes.
+ *
+ * Firmware expects a somewhat literal encoding of this bit-vector
+ * structure, where each entry is stored in little-endian so that the
+ * byte ordering reflects that of the documentation, but where each bit
+ * offset is from "left-to-right" in the traditional representation of
+ * a byte value where the MSB is the left-most bit. Thus, each
+ * individual byte encodes the option bits in reverse order of the
+ * documented bit.
+ *
+ * These definitions/helpers attempt to abstract away this internal
+ * representation so that we can define/set/test for individual option
+ * bits using only the documented values. This is done mainly by relying
+ * on a bitmap to approximate the documented "bit-vector" structure and
+ * handling conversations to-from the internal representation under the
+ * covers.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Authors:
+ * Michael Roth <mdroth@linux.vnet.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#ifndef _SPAPR_OVEC_H
+#define _SPAPR_OVEC_H
+
+#include "cpu.h"
+
+typedef struct sPAPROptionVector sPAPROptionVector;
+
+#define OV_BIT(byte, bit) ((byte - 1) * BITS_PER_BYTE + bit)
+
+/* option vector 5 */
+#define OV5_DRCONF_MEMORY OV_BIT(2, 2)
+#define OV5_FORM1_AFFINITY OV_BIT(5, 0)
+#define OV5_HP_EVT OV_BIT(6, 5)
+
+/* interfaces */
+sPAPROptionVector *spapr_ovec_new(void);
+sPAPROptionVector *spapr_ovec_clone(sPAPROptionVector *ov_orig);
+void spapr_ovec_intersect(sPAPROptionVector *ov,
+ sPAPROptionVector *ov1,
+ sPAPROptionVector *ov2);
+bool spapr_ovec_diff(sPAPROptionVector *ov,
+ sPAPROptionVector *ov_old,
+ sPAPROptionVector *ov_new);
+void spapr_ovec_cleanup(sPAPROptionVector *ov);
+void spapr_ovec_set(sPAPROptionVector *ov, long bitnr);
+void spapr_ovec_clear(sPAPROptionVector *ov, long bitnr);
+bool spapr_ovec_test(sPAPROptionVector *ov, long bitnr);
+sPAPROptionVector *spapr_ovec_parse_vector(target_ulong table_addr, int vector);
+int spapr_ovec_populate_dt(void *fdt, int fdt_offset,
+ sPAPROptionVector *ov, const char *name);
+
+#endif /* !defined (_SPAPR_OVEC_H) */
diff --git a/include/hw/ppc/spapr_vio.h b/include/hw/ppc/spapr_vio.h
index 40d0e5f6a3..14f502240e 100644
--- a/include/hw/ppc/spapr_vio.h
+++ b/include/hw/ppc/spapr_vio.h
@@ -76,14 +76,12 @@ struct VIOsPAPRDevice {
struct VIOsPAPRBus {
BusState bus;
uint32_t next_reg;
- int (*init)(VIOsPAPRDevice *dev);
- int (*devnode)(VIOsPAPRDevice *dev, void *fdt, int node_off);
};
extern VIOsPAPRBus *spapr_vio_bus_init(void);
extern VIOsPAPRDevice *spapr_vio_find_by_reg(VIOsPAPRBus *bus, uint32_t reg);
-extern int spapr_populate_vdevice(VIOsPAPRBus *bus, void *fdt);
-extern int spapr_populate_chosen_stdout(void *fdt, VIOsPAPRBus *bus);
+void spapr_dt_vdevice(VIOsPAPRBus *bus, void *fdt);
+extern gchar *spapr_vio_stdout_path(VIOsPAPRBus *bus);
static inline qemu_irq spapr_vio_qirq(VIOsPAPRDevice *dev)
{
diff --git a/include/hw/ppc/xics.h b/include/hw/ppc/xics.h
index 66ae55ded3..3f0c31610a 100644
--- a/include/hw/ppc/xics.h
+++ b/include/hw/ppc/xics.h
@@ -117,6 +117,8 @@ struct ICPState {
uint8_t mfrr;
qemu_irq output;
bool cap_irq_xics_enabled;
+
+ XICSState *xics;
};
#define TYPE_ICS_BASE "ics-base"
@@ -185,18 +187,21 @@ int xics_spapr_alloc(XICSState *icp, int irq_hint, bool lsi, Error **errp);
int xics_spapr_alloc_block(XICSState *icp, int num, bool lsi, bool align,
Error **errp);
void xics_spapr_free(XICSState *icp, int irq, int num);
+void spapr_dt_xics(XICSState *xics, void *fdt, uint32_t phandle);
void xics_cpu_setup(XICSState *icp, PowerPCCPU *cpu);
void xics_cpu_destroy(XICSState *icp, PowerPCCPU *cpu);
+void xics_set_nr_servers(XICSState *xics, uint32_t nr_servers,
+ const char *typename, Error **errp);
/* Internal XICS interfaces */
int xics_get_cpu_index_by_dt_id(int cpu_dt_id);
-void icp_set_cppr(XICSState *icp, int server, uint8_t cppr);
-void icp_set_mfrr(XICSState *icp, int server, uint8_t mfrr);
+void icp_set_cppr(ICPState *icp, uint8_t cppr);
+void icp_set_mfrr(ICPState *icp, uint8_t mfrr);
uint32_t icp_accept(ICPState *ss);
uint32_t icp_ipoll(ICPState *ss, uint32_t *mfrr);
-void icp_eoi(XICSState *icp, int server, uint32_t xirr);
+void icp_eoi(ICPState *icp, uint32_t xirr);
void ics_simple_write_xive(ICSState *ics, int nr, int server,
uint8_t priority, uint8_t saved_priority);
diff --git a/include/hw/xen/xen_backend.h b/include/hw/xen/xen_backend.h
index 0df282ab5f..cbda40ee53 100644
--- a/include/hw/xen/xen_backend.h
+++ b/include/hw/xen/xen_backend.h
@@ -2,60 +2,10 @@
#define QEMU_HW_XEN_BACKEND_H
#include "hw/xen/xen_common.h"
+#include "hw/xen/xen_pvdev.h"
#include "sysemu/sysemu.h"
#include "net/net.h"
-/* ------------------------------------------------------------- */
-
-#define XEN_BUFSIZE 1024
-
-struct XenDevice;
-
-/* driver uses grant tables -> open gntdev device (xendev->gnttabdev) */
-#define DEVOPS_FLAG_NEED_GNTDEV 1
-/* don't expect frontend doing correct state transitions (aka console quirk) */
-#define DEVOPS_FLAG_IGNORE_STATE 2
-
-struct XenDevOps {
- size_t size;
- uint32_t flags;
- void (*alloc)(struct XenDevice *xendev);
- int (*init)(struct XenDevice *xendev);
- int (*initialise)(struct XenDevice *xendev);
- void (*connected)(struct XenDevice *xendev);
- void (*event)(struct XenDevice *xendev);
- void (*disconnect)(struct XenDevice *xendev);
- int (*free)(struct XenDevice *xendev);
- void (*backend_changed)(struct XenDevice *xendev, const char *node);
- void (*frontend_changed)(struct XenDevice *xendev, const char *node);
- int (*backend_register)(void);
-};
-
-struct XenDevice {
- const char *type;
- int dom;
- int dev;
- char name[64];
- int debug;
-
- enum xenbus_state be_state;
- enum xenbus_state fe_state;
- int online;
- char be[XEN_BUFSIZE];
- char *fe;
- char *protocol;
- int remote_port;
- int local_port;
-
- xenevtchn_handle *evtchndev;
- xengnttab_handle *gnttabdev;
-
- struct XenDevOps *ops;
- QTAILQ_ENTRY(XenDevice) next;
-};
-
-/* ------------------------------------------------------------- */
-
/* variables */
extern xc_interface *xen_xc;
extern xenforeignmemory_handle *xen_fmem;
@@ -63,26 +13,20 @@ extern struct xs_handle *xenstore;
extern const char *xen_protocol;
extern DeviceState *xen_sysdev;
-/* xenstore helper functions */
int xenstore_mkdir(char *path, int p);
-int xenstore_write_str(const char *base, const char *node, const char *val);
-int xenstore_write_int(const char *base, const char *node, int ival);
-int xenstore_write_int64(const char *base, const char *node, int64_t ival);
-char *xenstore_read_str(const char *base, const char *node);
-int xenstore_read_int(const char *base, const char *node, int *ival);
-
int xenstore_write_be_str(struct XenDevice *xendev, const char *node, const char *val);
int xenstore_write_be_int(struct XenDevice *xendev, const char *node, int ival);
int xenstore_write_be_int64(struct XenDevice *xendev, const char *node, int64_t ival);
char *xenstore_read_be_str(struct XenDevice *xendev, const char *node);
int xenstore_read_be_int(struct XenDevice *xendev, const char *node, int *ival);
+void xenstore_update_fe(char *watch, struct XenDevice *xendev);
+void xenstore_update_be(char *watch, char *type, int dom,
+ struct XenDevOps *ops);
char *xenstore_read_fe_str(struct XenDevice *xendev, const char *node);
int xenstore_read_fe_int(struct XenDevice *xendev, const char *node, int *ival);
-int xenstore_read_uint64(const char *base, const char *node, uint64_t *uval);
-int xenstore_read_fe_uint64(struct XenDevice *xendev, const char *node, uint64_t *uval);
+int xenstore_read_fe_uint64(struct XenDevice *xendev, const char *node,
+ uint64_t *uval);
-const char *xenbus_strstate(enum xenbus_state state);
-struct XenDevice *xen_be_find_xendev(const char *type, int dom, int dev);
void xen_be_check_state(struct XenDevice *xendev);
/* xen backend driver bits */
@@ -91,10 +35,6 @@ void xen_be_register_common(void);
int xen_be_register(const char *type, struct XenDevOps *ops);
int xen_be_set_state(struct XenDevice *xendev, enum xenbus_state state);
int xen_be_bind_evtchn(struct XenDevice *xendev);
-void xen_be_unbind_evtchn(struct XenDevice *xendev);
-int xen_be_send_notify(struct XenDevice *xendev);
-void xen_be_printf(struct XenDevice *xendev, int msg_level, const char *fmt, ...)
- GCC_FMT_ATTR(3, 4);
/* actual backend drivers */
extern struct XenDevOps xen_console_ops; /* xen_console.c */
diff --git a/include/hw/xen/xen_pvdev.h b/include/hw/xen/xen_pvdev.h
new file mode 100644
index 0000000000..083f0a9cc7
--- /dev/null
+++ b/include/hw/xen/xen_pvdev.h
@@ -0,0 +1,78 @@
+#ifndef QEMU_HW_XEN_PVDEV_H
+#define QEMU_HW_XEN_PVDEV_H
+
+#include "hw/xen/xen_common.h"
+/* ------------------------------------------------------------- */
+
+#define XEN_BUFSIZE 1024
+
+struct XenDevice;
+
+/* driver uses grant tables -> open gntdev device (xendev->gnttabdev) */
+#define DEVOPS_FLAG_NEED_GNTDEV 1
+/* don't expect frontend doing correct state transitions (aka console quirk) */
+#define DEVOPS_FLAG_IGNORE_STATE 2
+
+struct XenDevOps {
+ size_t size;
+ uint32_t flags;
+ void (*alloc)(struct XenDevice *xendev);
+ int (*init)(struct XenDevice *xendev);
+ int (*initialise)(struct XenDevice *xendev);
+ void (*connected)(struct XenDevice *xendev);
+ void (*event)(struct XenDevice *xendev);
+ void (*disconnect)(struct XenDevice *xendev);
+ int (*free)(struct XenDevice *xendev);
+ void (*backend_changed)(struct XenDevice *xendev, const char *node);
+ void (*frontend_changed)(struct XenDevice *xendev, const char *node);
+ int (*backend_register)(void);
+};
+
+struct XenDevice {
+ const char *type;
+ int dom;
+ int dev;
+ char name[64];
+ int debug;
+
+ enum xenbus_state be_state;
+ enum xenbus_state fe_state;
+ int online;
+ char be[XEN_BUFSIZE];
+ char *fe;
+ char *protocol;
+ int remote_port;
+ int local_port;
+
+ xenevtchn_handle *evtchndev;
+ xengnttab_handle *gnttabdev;
+
+ struct XenDevOps *ops;
+ QTAILQ_ENTRY(XenDevice) next;
+};
+
+/* ------------------------------------------------------------- */
+
+/* xenstore helper functions */
+int xenstore_write_str(const char *base, const char *node, const char *val);
+int xenstore_write_int(const char *base, const char *node, int ival);
+int xenstore_write_int64(const char *base, const char *node, int64_t ival);
+char *xenstore_read_str(const char *base, const char *node);
+int xenstore_read_int(const char *base, const char *node, int *ival);
+int xenstore_read_uint64(const char *base, const char *node, uint64_t *uval);
+void xenstore_update(void *unused);
+
+const char *xenbus_strstate(enum xenbus_state state);
+
+void xen_pv_evtchn_event(void *opaque);
+void xen_pv_insert_xendev(struct XenDevice *xendev);
+void xen_pv_del_xendev(struct XenDevice *xendev);
+struct XenDevice *xen_pv_find_xendev(const char *type, int dom, int dev);
+
+void xen_pv_unbind_evtchn(struct XenDevice *xendev);
+int xen_pv_send_notify(struct XenDevice *xendev);
+
+void xen_pv_printf(struct XenDevice *xendev, int msg_level,
+ const char *fmt, ...) GCC_FMT_ATTR(3, 4);
+
+#endif /* QEMU_HW_XEN_PVDEV_H */
diff --git a/include/io/channel.h b/include/io/channel.h
index 752e89f4dc..32a9470794 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -40,9 +40,9 @@ typedef struct QIOChannelClass QIOChannelClass;
typedef enum QIOChannelFeature QIOChannelFeature;
enum QIOChannelFeature {
- QIO_CHANNEL_FEATURE_FD_PASS = (1 << 0),
- QIO_CHANNEL_FEATURE_SHUTDOWN = (1 << 1),
- QIO_CHANNEL_FEATURE_LISTEN = (1 << 2),
+ QIO_CHANNEL_FEATURE_FD_PASS,
+ QIO_CHANNEL_FEATURE_SHUTDOWN,
+ QIO_CHANNEL_FEATURE_LISTEN,
};
@@ -79,6 +79,7 @@ typedef gboolean (*QIOChannelFunc)(QIOChannel *ioc,
struct QIOChannel {
Object parent;
unsigned int features; /* bitmask of QIOChannelFeatures */
+ char *name;
#ifdef _WIN32
HANDLE event; /* For use with GSource on Win32 */
#endif
@@ -149,6 +150,28 @@ bool qio_channel_has_feature(QIOChannel *ioc,
QIOChannelFeature feature);
/**
+ * qio_channel_set_feature:
+ * @ioc: the channel object
+ * @feature: the feature to set support for
+ *
+ * Add channel support for the feature named in @feature.
+ */
+void qio_channel_set_feature(QIOChannel *ioc,
+ QIOChannelFeature feature);
+
+/**
+ * qio_channel_set_name:
+ * @ioc: the channel object
+ * @name: the name of the channel
+ *
+ * Sets the name of the channel, which serves as an aid
+ * to debugging. The name is used when creating GSource
+ * watches for this channel.
+ */
+void qio_channel_set_name(QIOChannel *ioc,
+ const char *name);
+
+/**
* qio_channel_readv_full:
* @ioc: the channel object
* @iov: the array of memory regions to read data into
diff --git a/include/migration/colo.h b/include/migration/colo.h
new file mode 100644
index 0000000000..e32eef4763
--- /dev/null
+++ b/include/migration/colo.h
@@ -0,0 +1,38 @@
+/*
+ * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
+ * (a.k.a. Fault Tolerance or Continuous Replication)
+ *
+ * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
+ * Copyright (c) 2016 FUJITSU LIMITED
+ * Copyright (c) 2016 Intel Corporation
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later. See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_COLO_H
+#define QEMU_COLO_H
+
+#include "qemu-common.h"
+#include "migration/migration.h"
+#include "qemu/coroutine_int.h"
+#include "qemu/thread.h"
+#include "qemu/main-loop.h"
+
+bool colo_supported(void);
+void colo_info_init(void);
+
+void migrate_start_colo_process(MigrationState *s);
+bool migration_in_colo_state(void);
+
+/* loadvm */
+bool migration_incoming_enable_colo(void);
+void migration_incoming_exit_colo(void);
+void *colo_process_incoming_thread(void *opaque);
+bool migration_incoming_in_colo_state(void);
+
+COLOMode get_colo_mode(void);
+
+/* failover */
+void colo_do_failover(MigrationState *s);
+#endif
diff --git a/include/migration/failover.h b/include/migration/failover.h
new file mode 100644
index 0000000000..ad91ef2381
--- /dev/null
+++ b/include/migration/failover.h
@@ -0,0 +1,26 @@
+/*
+ * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
+ * (a.k.a. Fault Tolerance or Continuous Replication)
+ *
+ * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO.,LTD.
+ * Copyright (c) 2016 FUJITSU LIMITED
+ * Copyright (c) 2016 Intel Corporation
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later. See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_FAILOVER_H
+#define QEMU_FAILOVER_H
+
+#include "qemu-common.h"
+#include "qapi-types.h"
+
+void failover_init_state(void);
+FailoverStatus failover_set_state(FailoverStatus old_state,
+ FailoverStatus new_state);
+FailoverStatus failover_get_state(void);
+void failover_request_active(Error **errp);
+bool failover_request_is_active(void);
+
+#endif
diff --git a/include/migration/migration.h b/include/migration/migration.h
index 2791b90c00..c309d23370 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -21,6 +21,7 @@
#include "migration/vmstate.h"
#include "qapi-types.h"
#include "exec/cpu-common.h"
+#include "qemu/coroutine_int.h"
#define QEMU_VM_FILE_MAGIC 0x5145564d
#define QEMU_VM_FILE_VERSION_COMPAT 0x00000002
@@ -107,6 +108,12 @@ struct MigrationIncomingState {
QEMUBH *bh;
int state;
+
+ bool have_colo_incoming_thread;
+ QemuThread colo_incoming_thread;
+ /* The coroutine we should enter (back) after failover */
+ Coroutine *migration_incoming_co;
+
/* See savevm.c */
LoadStateEntry_Head loadvm_handlers;
};
@@ -298,6 +305,7 @@ int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen);
int migrate_use_xbzrle(void);
int64_t migrate_xbzrle_cache_size(void);
+bool migrate_colo_enabled(void);
int64_t xbzrle_cache_resize(int64_t new_size);
diff --git a/include/monitor/monitor.h b/include/monitor/monitor.h
index a714d8ef80..8cc532ec0e 100644
--- a/include/monitor/monitor.h
+++ b/include/monitor/monitor.h
@@ -9,7 +9,7 @@
extern Monitor *cur_mon;
/* flags for monitor_init */
-#define MONITOR_IS_DEFAULT 0x01
+/* 0x01 unused */
#define MONITOR_USE_READLINE 0x02
#define MONITOR_USE_CONTROL 0x04
#define MONITOR_USE_PRETTY 0x08
diff --git a/include/qemu/rfifolock.h b/include/qemu/rfifolock.h
deleted file mode 100644
index b23ab538a6..0000000000
--- a/include/qemu/rfifolock.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Recursive FIFO lock
- *
- * Copyright Red Hat, Inc. 2013
- *
- * Authors:
- * Stefan Hajnoczi <stefanha@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#ifndef QEMU_RFIFOLOCK_H
-#define QEMU_RFIFOLOCK_H
-
-#include "qemu/thread.h"
-
-/* Recursive FIFO lock
- *
- * This lock provides more features than a plain mutex:
- *
- * 1. Fairness - enforces FIFO order.
- * 2. Nesting - can be taken recursively.
- * 3. Contention callback - optional, called when thread must wait.
- *
- * The recursive FIFO lock is heavyweight so prefer other synchronization
- * primitives if you do not need its features.
- */
-typedef struct {
- QemuMutex lock; /* protects all fields */
-
- /* FIFO order */
- unsigned int head; /* active ticket number */
- unsigned int tail; /* waiting ticket number */
- QemuCond cond; /* used to wait for our ticket number */
-
- /* Nesting */
- QemuThread owner_thread; /* thread that currently has ownership */
- unsigned int nesting; /* amount of nesting levels */
-
- /* Contention callback */
- void (*cb)(void *); /* called when thread must wait, with ->lock
- * held so it may not recursively lock/unlock
- */
- void *cb_opaque;
-} RFifoLock;
-
-void rfifolock_init(RFifoLock *r, void (*cb)(void *), void *opaque);
-void rfifolock_destroy(RFifoLock *r);
-void rfifolock_lock(RFifoLock *r);
-void rfifolock_unlock(RFifoLock *r);
-
-#endif /* QEMU_RFIFOLOCK_H */
diff --git a/include/qemu/thread-posix.h b/include/qemu/thread-posix.h
index aa03567e5e..09d1e15728 100644
--- a/include/qemu/thread-posix.h
+++ b/include/qemu/thread-posix.h
@@ -4,6 +4,12 @@
#include <pthread.h>
#include <semaphore.h>
+typedef QemuMutex QemuRecMutex;
+#define qemu_rec_mutex_destroy qemu_mutex_destroy
+#define qemu_rec_mutex_lock qemu_mutex_lock
+#define qemu_rec_mutex_try_lock qemu_mutex_try_lock
+#define qemu_rec_mutex_unlock qemu_mutex_unlock
+
struct QemuMutex {
pthread_mutex_t lock;
};
diff --git a/include/qemu/thread-win32.h b/include/qemu/thread-win32.h
index c7ce8dcd45..5fb6541ae9 100644
--- a/include/qemu/thread-win32.h
+++ b/include/qemu/thread-win32.h
@@ -8,6 +8,16 @@ struct QemuMutex {
LONG owner;
};
+typedef struct QemuRecMutex QemuRecMutex;
+struct QemuRecMutex {
+ CRITICAL_SECTION lock;
+};
+
+void qemu_rec_mutex_destroy(QemuRecMutex *mutex);
+void qemu_rec_mutex_lock(QemuRecMutex *mutex);
+int qemu_rec_mutex_trylock(QemuRecMutex *mutex);
+void qemu_rec_mutex_unlock(QemuRecMutex *mutex);
+
struct QemuCond {
LONG waiters, target;
HANDLE sema;
diff --git a/include/qemu/thread.h b/include/qemu/thread.h
index 31237e93ee..e8e665f020 100644
--- a/include/qemu/thread.h
+++ b/include/qemu/thread.h
@@ -25,6 +25,9 @@ void qemu_mutex_lock(QemuMutex *mutex);
int qemu_mutex_trylock(QemuMutex *mutex);
void qemu_mutex_unlock(QemuMutex *mutex);
+/* Prototypes for other functions are in thread-posix.h/thread-win32.h. */
+void qemu_rec_mutex_init(QemuRecMutex *mutex);
+
void qemu_cond_init(QemuCond *cond);
void qemu_cond_destroy(QemuCond *cond);
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index b07159b639..6444e41d39 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -146,6 +146,7 @@ BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int count,
BlockCompletionFunc *cb, void *opaque);
void blk_aio_cancel(BlockAIOCB *acb);
void blk_aio_cancel_async(BlockAIOCB *acb);
+int blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf);
BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
BlockCompletionFunc *cb, void *opaque);
diff --git a/include/sysemu/dma.h b/include/sysemu/dma.h
index 34c8eaf64e..c228c66513 100644
--- a/include/sysemu/dma.h
+++ b/include/sysemu/dma.h
@@ -199,14 +199,14 @@ typedef BlockAIOCB *DMAIOFunc(int64_t offset, QEMUIOVector *iov,
void *opaque);
BlockAIOCB *dma_blk_io(AioContext *ctx,
- QEMUSGList *sg, uint64_t offset,
+ QEMUSGList *sg, uint64_t offset, uint32_t align,
DMAIOFunc *io_func, void *io_func_opaque,
BlockCompletionFunc *cb, void *opaque, DMADirection dir);
BlockAIOCB *dma_blk_read(BlockBackend *blk,
- QEMUSGList *sg, uint64_t offset,
+ QEMUSGList *sg, uint64_t offset, uint32_t align,
BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *dma_blk_write(BlockBackend *blk,
- QEMUSGList *sg, uint64_t offset,
+ QEMUSGList *sg, uint64_t offset, uint32_t align,
BlockCompletionFunc *cb, void *opaque);
uint64_t dma_buf_read(uint8_t *ptr, int32_t len, QEMUSGList *sg);
uint64_t dma_buf_write(uint8_t *ptr, int32_t len, QEMUSGList *sg);